Raw scan report

Xactions — the complete, unedited output of the deterministic mcptrustchecker engine v1.13.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.

← Back to the scan page
{
  "tool": {
    "name": "mcptrustchecker",
    "version": "1.13.0",
    "methodologyVersion": "mcptrustchecker-1.13"
  },
  "target": {
    "id": "xactions",
    "source": {
      "kind": "package",
      "origin": "xactions"
    },
    "server": {
      "name": "xactions"
    }
  },
  "grade": "B",
  "score": {
    "score": 83,
    "threatScore": 94,
    "grade": "B",
    "band": "B",
    "categorySubtotals": {
      "injection": 6.3,
      "exfiltration": 0,
      "permissions": 0,
      "supply-chain": 0,
      "network": 0,
      "hygiene": 0
    },
    "vector": [
      {
        "kind": "threat",
        "ruleId": "MTC-SRC-009",
        "category": "injection",
        "severity": "medium",
        "confidence": "strong",
        "rawWeight": 9,
        "confidenceMult": 0.7,
        "diminishingFactor": 1,
        "appliedPenalty": 6.3
      },
      {
        "kind": "client",
        "term": "capability-exposure",
        "level": "critical",
        "label": "capability blast radius (critical) — client exposure if the model is manipulated",
        "appliedPenalty": 10
      },
      {
        "kind": "client",
        "term": "verification-discount",
        "level": "repo",
        "label": "publisher verification (public source) — no provenance, but the source is public and inspectable",
        "appliedPenalty": 1
      },
      {
        "kind": "client",
        "term": "coverage-honesty",
        "level": "source",
        "label": "inspection depth (source) — how much of the target the scan could see",
        "appliedPenalty": 0
      }
    ],
    "gatesFired": [],
    "methodologyVersion": "mcptrustchecker-1.13"
  },
  "capability": {
    "level": "critical",
    "reasons": [
      "ingests untrusted external content (a prompt-injection entry point)",
      "can send data / act on an external service",
      "can execute shell commands or code",
      "untrusted input can reach code execution"
    ],
    "tags": [
      "untrusted-input",
      "external-sink",
      "code-exec"
    ]
  },
  "coverage": {
    "level": "source",
    "inputs": {
      "toolSurface": true,
      "implementationSource": true,
      "packageMetadata": true,
      "liveTransport": false
    },
    "caveats": [
      "Tools were statically extracted from the published source (145 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command \"npx -y <package>\"."
    ]
  },
  "findings": [
    {
      "ruleId": "MTC-SRC-001",
      "title": "Dynamic code execution in server code (src/scrapers/adapters/got-jsdom.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/scrapers/adapters/got-jsdom.js:206`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "src/scrapers/adapters/got-jsdom.js"
      },
      "evidence": "const wrappedFn = new Function('window', 'document', 'navigator', ...args.map((_, i) => `__arg${i}`), `con",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-001",
        "file": "src/scrapers/adapters/got-jsdom.js",
        "line": 206,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/plugins/manager.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/plugins/manager.js:11`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "src/plugins/manager.js"
      },
      "evidence": "port { execSync } from 'child_process'; import { readPluginsConfig, writePluginsConfig, loadPlugin, loadAllPlugi",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/plugins/manager.js",
        "line": 11,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/scheduler/scheduler.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/scheduler/scheduler.js:13`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "src/scheduler/scheduler.js"
      },
      "evidence": "execFile, spawn } from 'child_process'; import fs from 'fs'; import fsp from 'fs/promises'; import path from 'path'; imp",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/scheduler/scheduler.js",
        "line": 13,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-FLOW-005",
      "title": "Untrusted input can drive an external action",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "Untrusted-input tools ([x_get_followers, x_get_following, x_get_tweets, x_download_video, x_get_explore, x_get_notifications, x_scrape_space, x_get_thread, x_rss_add, x_rss_check, x_rss_drafts, x_get_replies, x_get_hashtag, x_get_media, x_get_mentions, x_get_likes]) co-exist with external-action tools ([x_post_tweet, x_like, x_retweet, x_download_video, x_post_thread, x_create_poll, x_schedule_post, x_delete_tweet, x_reply, x_bookmark, x_monitor_reputation, x_stream_start, x_get_thread, x_best_time_to_post, x_generate_tweet, x_rewrite_tweet, x_history_get, x_optimize_tweet, x_suggest_hashtags, x_predict_performance, x_generate_variations, x_get_replies, x_get_likers, x_get_retweeters, x_get_quote_tweets, x_quote_tweet, x_detect_bots, x_track_engagement]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.",
      "remediation": "Require confirmation for state-changing/egress actions triggered after processing untrusted content.",
      "location": {
        "kind": "flow",
        "name": "x_get_followers → x_post_tweet"
      },
      "evidence": "untrusted [x_get_followers, x_get_following, x_get_tweets, x_download_video, x_get_explore, x_get_notifications, x_scrape_space, x_get_thread, x_rss_add, x_rss_",
      "owasp": "LLM06:2025 Excessive Agency",
      "references": [],
      "data": {
        "untrusted": [
          "x_get_followers",
          "x_get_following",
          "x_get_tweets",
          "x_download_video",
          "x_get_explore",
          "x_get_notifications",
          "x_scrape_space",
          "x_get_thread",
          "x_rss_add",
          "x_rss_check",
          "x_rss_drafts",
          "x_get_replies",
          "x_get_hashtag",
          "x_get_media",
          "x_get_mentions",
          "x_get_likes"
        ],
        "sinks": [
          "x_post_tweet",
          "x_like",
          "x_retweet",
          "x_download_video",
          "x_post_thread",
          "x_create_poll",
          "x_schedule_post",
          "x_delete_tweet",
          "x_reply",
          "x_bookmark",
          "x_monitor_reputation",
          "x_stream_start",
          "x_get_thread",
          "x_best_time_to_post",
          "x_generate_tweet",
          "x_rewrite_tweet",
          "x_history_get",
          "x_optimize_tweet",
          "x_suggest_hashtags",
          "x_predict_performance",
          "x_generate_variations",
          "x_get_replies",
          "x_get_likers",
          "x_get_retweeters",
          "x_get_quote_tweets",
          "x_quote_tweet",
          "x_detect_bots",
          "x_track_engagement"
        ]
      }
    },
    {
      "ruleId": "MTC-SRC-003",
      "title": "Hardcoded egress to an external endpoint (src/analytics/sentiment.js)",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "In the server's implementation (`src/analytics/sentiment.js:248`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "src/analytics/sentiment.js"
      },
      "evidence": "const response = await fetch('https://openrouter.ai/api/v1/chat/completions', { method: 'POST', headers: {",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-003",
        "file": "src/analytics/sentiment.js",
        "line": 248,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-003",
      "title": "Hardcoded egress to an external endpoint (src/automation/controlPanel.js)",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "In the server's implementation (`src/automation/controlPanel.js:767`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "src/automation/controlPanel.js"
      },
      "evidence": "const res = await fetch('https://openrouter.ai/api/v1/chat/completions', { method: 'POST', hea",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-003",
        "file": "src/automation/controlPanel.js",
        "line": 767,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-003",
      "title": "Hardcoded egress to an external endpoint (src/mcp/server.js)",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "In the server's implementation (`src/mcp/server.js:2786`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "src/mcp/server.js"
      },
      "evidence": "const response = await fetch('https://openrouter.ai/api/v1/chat/completions', { method: 'POST', headers",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-003",
        "file": "src/mcp/server.js",
        "line": 2786,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-003",
      "title": "Hardcoded egress to an external endpoint (src/notifications/notifier.js)",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "In the server's implementation (`src/notifications/notifier.js:203`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "src/notifications/notifier.js"
      },
      "evidence": "const response = await fetch(`https://api.telegram.org/bot${botToken}/sendMessage`, { method: 'POST', heade",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-003",
        "file": "src/notifications/notifier.js",
        "line": 203,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-003",
      "title": "Hardcoded egress to an external endpoint (src/scrapers/twitter/http/guest.js)",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "In the server's implementation (`src/scrapers/twitter/http/guest.js:206`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "src/scrapers/twitter/http/guest.js"
      },
      "evidence": "const res = await this.#fetch( 'https://api.x.com/1.1/guest/activate.json', { method: 'POST',",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-003",
        "file": "src/scrapers/twitter/http/guest.js",
        "line": 206,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-003",
      "title": "Hardcoded egress to an external endpoint (src/scraping/proxyManager.js)",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "In the server's implementation (`src/scraping/proxyManager.js:159`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "src/scraping/proxyManager.js"
      },
      "evidence": "10000); await fetch('https://httpbin.org/ip', { signal: controller.signal, // Note: fe",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-003",
        "file": "src/scraping/proxyManager.js",
        "line": 159,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-003",
      "title": "Hardcoded egress to an external endpoint (src/shadowbanChecker.js)",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "In the server's implementation (`src/shadowbanChecker.js:145`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "src/shadowbanChecker.js"
      },
      "evidence": "t typeaheadResp = await fetch( `https://x.com/i/api/1.1/search/typeahead.json?q=${username}&src=search_box&resul",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-003",
        "file": "src/shadowbanChecker.js",
        "line": 145,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-003",
      "title": "Hardcoded egress to an external endpoint (src/workflows/actions.js)",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "In the server's implementation (`src/workflows/actions.js:623`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "src/workflows/actions.js"
      },
      "evidence": "const response = await fetch('https://openrouter.ai/api/v1/chat/completions', { method: 'POST', headers: {",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-003",
        "file": "src/workflows/actions.js",
        "line": 623,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-009",
      "title": "Untrusted input concatenated into a command sink (src/plugins/manager.js)",
      "category": "injection",
      "severity": "medium",
      "confidence": "strong",
      "description": "In the server's implementation (`src/plugins/manager.js:66`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "src/plugins/manager.js"
      },
      "evidence": "ocal) { try { execSync(`npm install ${name}`, { stdio: 'pipe', cwd: process.cwd() }); } catch (error) {",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-009",
        "file": "src/plugins/manager.js",
        "line": 66,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-CAP-007",
      "title": "Unconstrained URL/host parameter \"url\" on \"x_like\"",
      "category": "network",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "Tool \"x_like\" takes a URL/host parameter \"url\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
      "remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
      "location": {
        "kind": "tool",
        "name": "x_like",
        "field": "inputSchema.properties.url"
      },
      "owasp": "LLM06:2025 Excessive Agency",
      "data": {
        "param": "url"
      }
    },
    {
      "ruleId": "MTC-CAP-007",
      "title": "Unconstrained URL/host parameter \"url\" on \"x_retweet\"",
      "category": "network",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "Tool \"x_retweet\" takes a URL/host parameter \"url\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
      "remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
      "location": {
        "kind": "tool",
        "name": "x_retweet",
        "field": "inputSchema.properties.url"
      },
      "owasp": "LLM06:2025 Excessive Agency",
      "data": {
        "param": "url"
      }
    },
    {
      "ruleId": "MTC-CAP-007",
      "title": "Unconstrained URL/host parameter \"url\" on \"x_delete_tweet\"",
      "category": "network",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "Tool \"x_delete_tweet\" takes a URL/host parameter \"url\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
      "remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
      "location": {
        "kind": "tool",
        "name": "x_delete_tweet",
        "field": "inputSchema.properties.url"
      },
      "owasp": "LLM06:2025 Excessive Agency",
      "data": {
        "param": "url"
      }
    },
    {
      "ruleId": "MTC-CAP-007",
      "title": "Unconstrained URL/host parameter \"url\" on \"x_reply\"",
      "category": "network",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "Tool \"x_reply\" takes a URL/host parameter \"url\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
      "remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
      "location": {
        "kind": "tool",
        "name": "x_reply",
        "field": "inputSchema.properties.url"
      },
      "owasp": "LLM06:2025 Excessive Agency",
      "data": {
        "param": "url"
      }
    },
    {
      "ruleId": "MTC-CAP-007",
      "title": "Unconstrained URL/host parameter \"url\" on \"x_bookmark\"",
      "category": "network",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "Tool \"x_bookmark\" takes a URL/host parameter \"url\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
      "remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
      "location": {
        "kind": "tool",
        "name": "x_bookmark",
        "field": "inputSchema.properties.url"
      },
      "owasp": "LLM06:2025 Excessive Agency",
      "data": {
        "param": "url"
      }
    },
    {
      "ruleId": "MTC-CAP-007",
      "title": "Unconstrained URL/host parameter \"url\" on \"x_scrape_space\"",
      "category": "network",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "Tool \"x_scrape_space\" takes a URL/host parameter \"url\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
      "remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
      "location": {
        "kind": "tool",
        "name": "x_scrape_space",
        "field": "inputSchema.properties.url"
      },
      "owasp": "LLM06:2025 Excessive Agency",
      "data": {
        "param": "url"
      }
    },
    {
      "ruleId": "MTC-CAP-007",
      "title": "Unconstrained URL/host parameter \"url\" on \"x_get_thread\"",
      "category": "network",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "Tool \"x_get_thread\" takes a URL/host parameter \"url\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
      "remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
      "location": {
        "kind": "tool",
        "name": "x_get_thread",
        "field": "inputSchema.properties.url"
      },
      "owasp": "LLM06:2025 Excessive Agency",
      "data": {
        "param": "url"
      }
    },
    {
      "ruleId": "MTC-CAP-007",
      "title": "Unconstrained URL/host parameter \"url\" on \"x_rss_add\"",
      "category": "network",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "Tool \"x_rss_add\" takes a URL/host parameter \"url\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
      "remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
      "location": {
        "kind": "tool",
        "name": "x_rss_add",
        "field": "inputSchema.properties.url"
      },
      "owasp": "LLM06:2025 Excessive Agency",
      "data": {
        "param": "url"
      }
    },
    {
      "ruleId": "MTC-SRC-005",
      "title": "Dynamic module load from a non-literal (src/plugins/loader.js)",
      "category": "permissions",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "In the server's implementation (`src/plugins/loader.js:120`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "src/plugins/loader.js"
      },
      "evidence": "ath)}`; mod = await import(resolved); } else { // Load as npm package — use createRequire to resolve from cwd",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-005",
        "file": "src/plugins/loader.js",
        "line": 120,
        "nonRuntime": false
      }
    }
  ],
  "toxicFlows": [
    {
      "id": "flow-1",
      "severity": "medium",
      "confidence": "strong",
      "untrustedInput": [
        "x_get_followers",
        "x_get_following",
        "x_get_tweets",
        "x_download_video",
        "x_get_explore",
        "x_get_notifications",
        "x_scrape_space",
        "x_get_thread",
        "x_rss_add",
        "x_rss_check",
        "x_rss_drafts",
        "x_get_replies",
        "x_get_hashtag",
        "x_get_media",
        "x_get_mentions",
        "x_get_likes"
      ],
      "sensitiveSource": [],
      "externalSink": [
        "x_post_tweet",
        "x_like",
        "x_retweet",
        "x_download_video",
        "x_post_thread",
        "x_create_poll",
        "x_schedule_post",
        "x_delete_tweet",
        "x_reply",
        "x_bookmark",
        "x_monitor_reputation",
        "x_stream_start",
        "x_get_thread",
        "x_best_time_to_post",
        "x_generate_tweet",
        "x_rewrite_tweet",
        "x_history_get",
        "x_optimize_tweet",
        "x_suggest_hashtags",
        "x_predict_performance",
        "x_generate_variations",
        "x_get_replies",
        "x_get_likers",
        "x_get_retweeters",
        "x_get_quote_tweets",
        "x_quote_tweet",
        "x_detect_bots",
        "x_track_engagement"
      ],
      "selfContained": false,
      "description": "Untrusted input can drive an external action even though no sensitive source is exposed."
    }
  ],
  "capabilities": [
    {
      "tool": "x_login",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_get_profile",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_get_followers",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"scrape\""
        ]
      }
    },
    {
      "tool": "x_get_following",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"scrape\""
        ]
      }
    },
    {
      "tool": "x_get_non_followers",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_get_tweets",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"scrape\""
        ]
      }
    },
    {
      "tool": "x_search_tweets",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_follow",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_unfollow",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_unfollow_non_followers",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_detect_unfollowers",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_post_tweet",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_like",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_retweet",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_download_video",
      "tags": [
        "untrusted-input",
        "external-sink"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"download\""
        ],
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_update_profile",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_post_thread",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_create_poll",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_schedule_post",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_delete_tweet",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_reply",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_bookmark",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_get_bookmarks",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_clear_bookmarks",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_auto_like",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_get_trends",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_get_explore",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"scrape\""
        ]
      }
    },
    {
      "tool": "x_get_notifications",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"scrape\""
        ]
      }
    },
    {
      "tool": "x_mute_user",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_unmute_user",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_send_dm",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_get_conversations",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_export_dms",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_grok_query",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_grok_summarize",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_get_lists",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_get_list_members",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_get_spaces",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_scrape_space",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"scrape\""
        ]
      }
    },
    {
      "tool": "x_space_join",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_space_leave",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_space_status",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_space_transcript",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_get_analytics",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_get_post_analytics",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_get_settings",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_toggle_protected",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_get_blocked",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_brand_monitor",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_competitor_analysis",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_check_premium",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_publish_article",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_creator_analytics",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_analyze_sentiment",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_monitor_reputation",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"webhook\""
        ]
      }
    },
    {
      "tool": "x_reputation_report",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_stream_start",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_stream_stop",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_stream_list",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_stream_pause",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_stream_resume",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_stream_status",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_stream_history",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_workflow_create",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_workflow_run",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_workflow_list",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_workflow_actions",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_export_account",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_migrate_account",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_diff_exports",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_get_thread",
      "tags": [
        "untrusted-input",
        "external-sink"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"scrape\""
        ],
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_best_time_to_post",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_account_report",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_analyze_voice",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_generate_tweet",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_rewrite_tweet",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_summarize_thread",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_list_platforms",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_graph_build",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_graph_analyze",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_graph_recommendations",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_graph_list",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_persona_create",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_persona_list",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_persona_status",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_persona_edit",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_persona_delete",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_persona_run",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_persona_presets",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_history_get",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_history_snapshot",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_growth_rate",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_compare_accounts",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_audience_overlap",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_crm_sync",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_crm_tag",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_crm_search",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_crm_segment",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_bulk_execute",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_schedule_add",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_schedule_list",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_schedule_remove",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_evergreen_analyze",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_rss_add",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"rss\""
        ]
      }
    },
    {
      "tool": "x_rss_check",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"rss\""
        ]
      }
    },
    {
      "tool": "x_rss_drafts",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"rss\""
        ]
      }
    },
    {
      "tool": "x_optimize_tweet",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_suggest_hashtags",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_predict_performance",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_generate_variations",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_notify_send",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_notify_test",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_dataset_list",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_dataset_get",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_team_create",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_team_members",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_import_data",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_convert_format",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_get_replies",
      "tags": [
        "untrusted-input",
        "external-sink"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"scrape\""
        ],
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_get_hashtag",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"scrape\""
        ]
      }
    },
    {
      "tool": "x_get_likers",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_get_retweeters",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_get_media",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"scrape\""
        ]
      }
    },
    {
      "tool": "x_get_recommendations",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_get_mentions",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"scrape\""
        ]
      }
    },
    {
      "tool": "x_get_quote_tweets",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_get_likes",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"scrape\""
        ]
      }
    },
    {
      "tool": "x_auto_follow",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_follow_engagers",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_unfollow_all",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_smart_unfollow",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_quote_tweet",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_auto_comment",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_auto_retweet",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_detect_bots",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    },
    {
      "tool": "x_find_influencers",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_smart_target",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_crypto_analyze",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_grok_analyze_image",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_audience_insights",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_engagement_report",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_monitor_account",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_monitor_keyword",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_follower_alerts",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "x_track_engagement",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"tweet\""
        ]
      }
    }
  ],
  "surfaceDigest": "6c4755ff871504924de8c5b32a3060ff67a78fce9507ccc2dc4208f1cfafcd67",
  "stats": {
    "tools": 145,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 3,
      "medium": 19,
      "low": 0,
      "info": 0
    }
  }
}