Raw scan report

Mund — 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": "@weave_protocol/mund",
    "source": {
      "kind": "package",
      "origin": "@weave_protocol/mund"
    },
    "server": {
      "name": "@weave_protocol/mund"
    }
  },
  "grade": "C",
  "score": {
    "score": 76,
    "threatScore": 82,
    "grade": "C",
    "band": "C",
    "categorySubtotals": {
      "injection": 2.4,
      "exfiltration": 15.4,
      "permissions": 0,
      "supply-chain": 0,
      "network": 0,
      "hygiene": 0
    },
    "vector": [
      {
        "kind": "threat",
        "ruleId": "MTC-INJ-AUTH-2",
        "category": "injection",
        "severity": "low",
        "confidence": "heuristic",
        "rawWeight": 3,
        "confidenceMult": 0.4,
        "diminishingFactor": 1,
        "appliedPenalty": 1.2
      },
      {
        "kind": "threat",
        "ruleId": "MTC-INJ-CMD-1",
        "category": "injection",
        "severity": "low",
        "confidence": "heuristic",
        "rawWeight": 3,
        "confidenceMult": 0.4,
        "diminishingFactor": 1,
        "appliedPenalty": 1.2
      },
      {
        "kind": "threat",
        "ruleId": "MTC-INJ-SECRET-1",
        "category": "exfiltration",
        "severity": "high",
        "confidence": "strong",
        "rawWeight": 22,
        "confidenceMult": 0.7,
        "diminishingFactor": 1,
        "appliedPenalty": 15.4
      },
      {
        "kind": "client",
        "term": "capability-exposure",
        "level": "high",
        "label": "capability blast radius (high) — client exposure if the model is manipulated",
        "appliedPenalty": 6
      },
      {
        "kind": "client",
        "term": "verification-discount",
        "level": "source",
        "label": "publisher verification (provenance) — cryptographic build provenance ties the artifact to its source",
        "appliedPenalty": 0
      },
      {
        "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": "high",
    "reasons": [
      "can send data / act on an external service",
      "can execute shell commands or code"
    ],
    "tags": [
      "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 (15 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-INJ-SECRET-1",
      "title": "Embedded AWS access key id in description",
      "category": "exfiltration",
      "severity": "high",
      "confidence": "strong",
      "description": "A live-looking AWS access key id is embedded in the description of tool \"mund_scan_content\". Hardcoded credentials in server metadata leak to every client that lists this server.",
      "remediation": "Remove the credential and rotate it; never ship secrets in tool metadata.",
      "location": {
        "kind": "tool",
        "name": "mund_scan_content",
        "field": "description"
      },
      "evidence": "AWS access key id: AKIA…(redacted)",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "secretType": "aws-access-key",
        "staticProvenanceCap": true
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/analyzers/mcp-server-analyzer.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/analyzers/mcp-server-analyzer.js:65`): 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": "dist/analyzers/mcp-server-analyzer.js"
      },
      "evidence": "' }, { pattern: /\\b(child_process|subprocess|system\\(|popen)\\b/i, capability: 'execution', risk: 'Process spawning'",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/analyzers/mcp-server-analyzer.js",
        "line": 65,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/constants.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/constants.js:403`): 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": "dist/constants.js"
      },
      "evidence": "pattern: '(?i)(child_process\\\\.exec|os\\\\.system|subprocess\\\\.call|eval\\\\(|exec\\\\().*\\\\$|.*\\\\{.*\\\\}', se",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/constants.js",
        "line": 403,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/analyzers/mcp-server-analyzer.ts)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/analyzers/mcp-server-analyzer.ts:146`): 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/analyzers/mcp-server-analyzer.ts"
      },
      "evidence": "on' }, { pattern: /\\b(child_process|subprocess|system\\(|popen)\\b/i, capability: 'execution', risk: 'Process spawning'",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/analyzers/mcp-server-analyzer.ts",
        "line": 146,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/constants.ts)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/constants.ts:416`): 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/constants.ts"
      },
      "evidence": "rn', pattern: '(?i)(child_process\\\\.exec|os\\\\.system|subprocess\\\\.call|eval\\\\(|exec\\\\().*\\\\$|.*\\\\{.*\\\\}', severi",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/constants.ts",
        "line": 416,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-INJ-AUTH-2",
      "title": "Instruction-override directive",
      "category": "injection",
      "severity": "low",
      "confidence": "heuristic",
      "description": "Instruction-override directive detected in the description of tool \"mund_scan_content\". Instruction-like content in tool metadata is executed by the model, not the human, and is the primary tool-poisoning vector.",
      "remediation": "Tool descriptions should describe behavior, not instruct the assistant. Treat imperative / secrecy / sequencing language in metadata as hostile.",
      "location": {
        "kind": "tool",
        "name": "mund_scan_content",
        "field": "description"
      },
      "evidence": "ignore previous instructions",
      "owasp": "LLM01:2025 Prompt Injection",
      "data": {
        "kind": "override"
      }
    },
    {
      "ruleId": "MTC-INJ-CMD-1",
      "title": "Shell command embedded in tool metadata",
      "category": "injection",
      "severity": "low",
      "confidence": "heuristic",
      "description": "Shell command embedded in tool metadata detected in the description of tool \"mund_validate_command\". Instruction-like content in tool metadata is executed by the model, not the human, and is the primary tool-poisoning vector.",
      "remediation": "Tool descriptions should describe behavior, not instruct the assistant. Treat imperative / secrecy / sequencing language in metadata as hostile.",
      "location": {
        "kind": "tool",
        "name": "mund_validate_command",
        "field": "description"
      },
      "evidence": "rm -rf",
      "owasp": "LLM01:2025 Prompt Injection",
      "data": {
        "kind": "command-in-prose"
      }
    }
  ],
  "toxicFlows": [],
  "capabilities": [
    {
      "tool": "mund_add_rule",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mund_remove_rule",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mund_list_rules",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mund_acknowledge_alert",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mund_block_pattern",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mund_allowlist_pattern",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mund_configure_notification",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"webhook\""
        ]
      }
    },
    {
      "tool": "mund_scan_mcp_server",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mund_check_typosquatting",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mund_audit_mcp_permissions",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mund_scan_content",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mund_check_url",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mund_validate_command",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mund_get_events",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mund_get_status",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "4853b5ae85fda0a06769848153a8312657b85999abadb412379a67b997267a2e",
  "stats": {
    "tools": 15,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 5,
      "medium": 0,
      "low": 2,
      "info": 0
    }
  }
}