Raw scan report

Livespec — 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": "livespec-mcp",
    "source": {
      "kind": "package",
      "origin": "livespec-mcp"
    },
    "server": {
      "name": "livespec-mcp"
    }
  },
  "grade": "A",
  "score": {
    "score": 92,
    "threatScore": 100,
    "grade": "A",
    "band": "A",
    "categorySubtotals": {
      "injection": 0,
      "exfiltration": 0,
      "permissions": 0,
      "supply-chain": 0,
      "network": 0,
      "hygiene": 0
    },
    "vector": [
      {
        "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": "none",
        "label": "publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read",
        "appliedPenalty": 2
      },
      {
        "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-1.9"
  },
  "capability": {
    "level": "high",
    "reasons": [
      "can execute shell commands or code"
    ],
    "tags": [
      "code-exec"
    ]
  },
  "coverage": {
    "level": "source",
    "inputs": {
      "toolSurface": true,
      "implementationSource": true,
      "packageMetadata": true,
      "liveTransport": false
    },
    "caveats": [
      "Tools were statically extracted from the published source (22 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-002",
      "title": "Shell/command execution in server code (src/livespec_mcp/tools/analysis.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/livespec_mcp/tools/analysis.py:1717`): 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/livespec_mcp/tools/analysis.py"
      },
      "evidence": "try: proc = subprocess.run( # --name-status -M: detect renames so the OLD path (which holds the",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/livespec_mcp/tools/analysis.py",
        "line": 1717,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/livespec_mcp/tools/explorer.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/livespec_mcp/tools/explorer.py:116`): 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/livespec_mcp/tools/explorer.py"
      },
      "evidence": "try: proc = subprocess.run( [\"git\", \"-C\", ws_root, \"rev-parse\", \"--verify\", \"--quiet\", ref],",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/livespec_mcp/tools/explorer.py",
        "line": 116,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in packaging/dev tooling (bench/run.py)",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`bench/run.py:47`): 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": "bench/run.py"
      },
      "evidence": "rue, exist_ok=True) subprocess.run( [\"git\", \"clone\", \"--depth\", \"1\", \"--branch\", ref, repo, str(dest)],",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "bench/run.py",
        "line": 47,
        "nonRuntime": true
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in packaging/dev tooling (scripts/dogfood_v019.py)",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/dogfood_v019.py:248`): 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": "scripts/dogfood_v019.py"
      },
      "evidence": "subprocess proc = subprocess.run( [sys.executable, str(WS / \"scripts\" / \"pr_diff_impact.py\")], cwd",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "scripts/dogfood_v019.py",
        "line": 248,
        "nonRuntime": true
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in packaging/dev tooling (tests/test_audit_p4_regressions.py)",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_audit_p4_regressions.py:17`): 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": "tests/test_audit_p4_regressions.py"
      },
      "evidence": "args: str) -> None: subprocess.run([\"git\", \"-C\", str(ws), *args], capture_output=True, text=True, check=True) @pyt",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "tests/test_audit_p4_regressions.py",
        "line": 17,
        "nonRuntime": true
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in packaging/dev tooling (tests/test_git_diff.py)",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_git_diff.py:15`): 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": "tests/test_git_diff.py"
      },
      "evidence": "str) -> str: proc = subprocess.run( [\"git\", \"-C\", str(workspace), *args], capture_output=True,",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "tests/test_git_diff.py",
        "line": 15,
        "nonRuntime": true
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in packaging/dev tooling (tests/test_rf_trend.py)",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_rf_trend.py:27`): 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": "tests/test_rf_trend.py"
      },
      "evidence": "str) -> str: proc = subprocess.run( [\"git\", \"-C\", str(workspace), *args], capture_output=True,",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "tests/test_rf_trend.py",
        "line": 27,
        "nonRuntime": true
      }
    },
    {
      "ruleId": "MTC-SUP-011",
      "title": "Package declares no source repository",
      "category": "supply-chain",
      "severity": "info",
      "confidence": "strong",
      "description": "\"livespec-mcp\" declares no repository URL, so its published artifact cannot be compared against reviewable source.",
      "remediation": "Prefer packages that link to public, reviewable source.",
      "location": {
        "kind": "package",
        "name": "livespec-mcp"
      }
    }
  ],
  "toxicFlows": [],
  "capabilities": [
    {
      "tool": "find_symbol",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_symbol_source",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "who_calls",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "who_does_this_call",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "quick_orient",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "analyze_impact",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_project_overview",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "find_dead_code",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "find_endpoints",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "audit_coverage",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "find_orphan_tests",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "git_diff_impact",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "grep_in_indexed_files",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "agent_scratch",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "agent_scratch_clear",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "generate_docs",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_docs",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "export_documentation",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "export_explorer",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "index_project",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "search",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "embed_chunks",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "e1a047d02408d2c9063dc8a459c87ab4bae406aa8e429e686dbb484e7e079f55",
  "stats": {
    "tools": 22,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 2,
      "medium": 0,
      "low": 5,
      "info": 1
    }
  }
}