Raw scan report

X (Twitter) API Docs — the complete, unedited output of the deterministic mcptrustchecker engine v1.9.0, 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": "1.9.0",
    "methodologyVersion": "mcptrustchecker-1.9"
  },
  "target": {
    "id": "https://docs.x.com/mcp",
    "source": {
      "kind": "http",
      "origin": "https://docs.x.com/mcp"
    },
    "server": {
      "name": "X",
      "version": "1.0.0"
    }
  },
  "grade": "B",
  "score": {
    "score": 88,
    "threatScore": 94,
    "grade": "B",
    "band": "B",
    "categorySubtotals": {
      "injection": 0,
      "exfiltration": 0,
      "permissions": 6.3,
      "supply-chain": 0,
      "network": 0,
      "hygiene": 0
    },
    "vector": [
      {
        "kind": "threat",
        "ruleId": "MTC-CAP-003",
        "category": "permissions",
        "severity": "medium",
        "confidence": "strong",
        "rawWeight": 9,
        "confidenceMult": 0.7,
        "diminishingFactor": 1,
        "appliedPenalty": 6.3
      },
      {
        "kind": "client",
        "term": "capability-exposure",
        "level": "high",
        "label": "capability blast radius (high) — client exposure if the model is manipulated",
        "appliedPenalty": 6
      },
      {
        "kind": "client",
        "term": "coverage-honesty",
        "level": "live",
        "label": "inspection depth (live) — how much of the target the scan could see",
        "appliedPenalty": 0
      }
    ],
    "gatesFired": [],
    "methodologyVersion": "mcptrustchecker-1.9"
  },
  "capability": {
    "level": "high",
    "reasons": [
      "ingests untrusted external content (a prompt-injection entry point)",
      "can execute shell commands or code"
    ],
    "tags": [
      "untrusted-input",
      "code-exec"
    ]
  },
  "coverage": {
    "level": "live",
    "inputs": {
      "toolSurface": true,
      "implementationSource": false,
      "packageMetadata": false,
      "liveTransport": true
    },
    "caveats": []
  },
  "findings": [
    {
      "ruleId": "MTC-CAP-001",
      "title": "Tool \"query_docs_filesystem_x\" exposes command/code execution",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "Tool \"query_docs_filesystem_x\" appears to run shell commands or evaluate code (parameter \"command\"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.",
      "remediation": "Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.",
      "location": {
        "kind": "tool",
        "name": "query_docs_filesystem_x"
      },
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "tags": [
          "untrusted-input",
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-FLOW-005",
      "title": "Untrusted input can drive an external action",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "Untrusted-input tools ([query_docs_filesystem_x]) co-exist with external-action tools ([query_docs_filesystem_x]). 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": "query_docs_filesystem_x → query_docs_filesystem_x"
      },
      "evidence": "untrusted [query_docs_filesystem_x] → sinks [query_docs_filesystem_x]",
      "owasp": "LLM06:2025 Excessive Agency",
      "references": [],
      "data": {
        "untrusted": [
          "query_docs_filesystem_x"
        ],
        "sinks": [
          "query_docs_filesystem_x"
        ]
      }
    },
    {
      "ruleId": "MTC-CAP-003",
      "title": "Annotation contradicts behavior on \"query_docs_filesystem_x\"",
      "category": "permissions",
      "severity": "medium",
      "confidence": "strong",
      "description": "Tool \"query_docs_filesystem_x\" advertises readOnlyHint=true but its derived capabilities include state-modifying actions (untrusted-input, code-exec). Tool annotations are attacker-controllable and must never be trusted; a mismatch like this is exactly how a hostile server hides a destructive tool.",
      "remediation": "Ignore server-provided annotations for security decisions; gate destructive tools on explicit user consent.",
      "location": {
        "kind": "tool",
        "name": "query_docs_filesystem_x"
      },
      "owasp": "LLM06:2025 Excessive Agency",
      "data": {
        "tags": [
          "untrusted-input",
          "code-exec"
        ],
        "annotations": {
          "readOnlyHint": true,
          "destructiveHint": false,
          "idempotentHint": true,
          "openWorldHint": false
        }
      }
    },
    {
      "ruleId": "MTC-CAP-006",
      "title": "Unconstrained command parameter \"command\" on \"query_docs_filesystem_x\"",
      "category": "permissions",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "Tool \"query_docs_filesystem_x\" takes a command-shaped parameter \"command\" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.",
      "remediation": "Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.",
      "location": {
        "kind": "tool",
        "name": "query_docs_filesystem_x",
        "field": "inputSchema.properties.command"
      },
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "param": "command"
      }
    },
    {
      "ruleId": "MTC-NET-005",
      "title": "Remote HTTP MCP endpoint",
      "category": "network",
      "severity": "info",
      "confidence": "strong",
      "description": "Remote endpoint docs.x.com. MCP Trust Checker does not test server-side authentication/authorization; verify the endpoint requires auth.",
      "location": {
        "kind": "transport"
      }
    }
  ],
  "toxicFlows": [
    {
      "id": "flow-1",
      "severity": "medium",
      "confidence": "strong",
      "untrustedInput": [
        "query_docs_filesystem_x"
      ],
      "sensitiveSource": [],
      "externalSink": [
        "query_docs_filesystem_x"
      ],
      "selfContained": false,
      "description": "Untrusted input can drive an external action even though no sensitive source is exposed."
    }
  ],
  "capabilities": [
    {
      "tool": "search_x",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "query_docs_filesystem_x",
      "tags": [
        "untrusted-input",
        "code-exec"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"get_page\""
        ],
        "code-exec": [
          "parameter \"command\""
        ]
      }
    },
    {
      "tool": "submit_feedback",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "f074a9714abf479d999acdac087b8f39a74bdfd896cb00342044e382a7941a5c",
  "stats": {
    "tools": 3,
    "prompts": 0,
    "resources": 1,
    "findingsBySeverity": {
      "critical": 0,
      "high": 1,
      "medium": 3,
      "low": 0,
      "info": 1
    }
  }
}