Raw scan report

Meridian — 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": "meridian-mcp",
    "source": {
      "kind": "package",
      "origin": "meridian-mcp"
    },
    "server": {
      "name": "meridian-mcp"
    }
  },
  "grade": "A",
  "score": {
    "score": 93,
    "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": "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": "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 (14 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/meridian/context/builder.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/meridian/context/builder.py:154`): 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/meridian/context/builder.py"
      },
      "evidence": "try: result = subprocess.run( [\"git\", \"rev-parse\", \"HEAD\"], cwd=repository_path, captu",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/meridian/context/builder.py",
        "line": 154,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/meridian/ledger.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/meridian/ledger.py:567`): 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/meridian/ledger.py"
      },
      "evidence": "olve() result = subprocess.run( [\"git\", \"-C\", str(p), \"rev-parse\", \"--show-toplevel\"], c",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/meridian/ledger.py",
        "line": 567,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/meridian/remote_clone.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/meridian/remote_clone.py:173`): 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/meridian/remote_clone.py"
      },
      "evidence": "try: result = subprocess.run(cmd, capture_output=True, text=True, timeout=timeout_seconds, env=env) except",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/meridian/remote_clone.py",
        "line": 173,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/meridian/report/pdf_exporter.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/meridian/report/pdf_exporter.py:94`): 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/meridian/report/pdf_exporter.py"
      },
      "evidence": "setup)...\") subprocess.run([sys.executable, \"-m\", \"playwright\", \"install\", \"chromium\"], check=True)",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/meridian/report/pdf_exporter.py",
        "line": 94,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/meridian/scan_ledger/scan_history.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/meridian/scan_ledger/scan_history.py:83`): 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/meridian/scan_ledger/scan_history.py"
      },
      "evidence": "try: result = subprocess.run( [\"git\", \"-C\", str(resolved), \"rev-parse\", \"--show-toplevel\"],",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/meridian/scan_ledger/scan_history.py",
        "line": 83,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-003",
      "title": "Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_assessment_e2e.py)",
      "category": "exfiltration",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_assessment_e2e.py:109`): 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": "tests/test_assessment_e2e.py"
      },
      "evidence": "():\\n\" \" requests.get('https://api.example.com/data')\\n\" \" return {'email': '[email protected]'}\\n\"",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-003",
        "file": "tests/test_assessment_e2e.py",
        "line": 109,
        "nonRuntime": true
      }
    },
    {
      "ruleId": "MTC-SRC-003",
      "title": "Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_context_builder_e2e.py)",
      "category": "exfiltration",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_context_builder_e2e.py:33`): 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": "tests/test_context_builder_e2e.py"
      },
      "evidence": "file():\\n\" \" requests.get('https://api.example.com/data')\\n\" \" return {'email': '[email protected]'}\\n\"",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-003",
        "file": "tests/test_context_builder_e2e.py",
        "line": 33,
        "nonRuntime": true
      }
    },
    {
      "ruleId": "MTC-SRC-003",
      "title": "Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_engine_e2e.py)",
      "category": "exfiltration",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_engine_e2e.py:33`): 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": "tests/test_engine_e2e.py"
      },
      "evidence": "file():\\n\" \" requests.get('https://api.example.com/data')\\n\" \" return {'email': '[email protected]'}\\n\"",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-003",
        "file": "tests/test_engine_e2e.py",
        "line": 33,
        "nonRuntime": true
      }
    },
    {
      "ruleId": "MTC-SRC-003",
      "title": "Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_interpreter_prompt_builder.py)",
      "category": "exfiltration",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_interpreter_prompt_builder.py:29`): 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": "tests/test_interpreter_prompt_builder.py"
      },
      "evidence": "():\\n\" \" requests.get('https://api.example.com/data')\\n\" \" return {'email': '[email protected]'}\\n\"",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-003",
        "file": "tests/test_interpreter_prompt_builder.py",
        "line": 29,
        "nonRuntime": true
      }
    },
    {
      "ruleId": "MTC-SRC-003",
      "title": "Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_report_builder_and_exporters.py)",
      "category": "exfiltration",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_report_builder_and_exporters.py:236`): 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": "tests/test_report_builder_and_exporters.py"
      },
      "evidence": "():\\n\" \" requests.get('https://api.example.com/data')\\n\" \" return {'email': '[email protected]'}\\n\"",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-003",
        "file": "tests/test_report_builder_and_exporters.py",
        "line": 236,
        "nonRuntime": true
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in packaging/dev tooling (tests/test_assessment_boundary.py)",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_assessment_boundary.py:107`): 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_assessment_boundary.py"
      },
      "evidence": "args: str) -> None: subprocess.run( [\"git\", \"-C\", str(repo), *args], check=True, capture_output=True",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "tests/test_assessment_boundary.py",
        "line": 107,
        "nonRuntime": true
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in packaging/dev tooling (tests/test_cli.py)",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_cli.py:656`): 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_cli.py"
      },
      "evidence": "ONPATH\", \"\") proc = subprocess.run( [sys.executable, \"-c\", code], capture_output=True, env=env, timeout=120",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "tests/test_cli.py",
        "line": 656,
        "nonRuntime": true
      }
    }
  ],
  "toxicFlows": [],
  "capabilities": [
    {
      "tool": "scan_repository",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "scan_repository_from_url",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "start_scan",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "start_scan_from_url",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "continue_scan",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "generate_report",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "repository_profile",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "technology_inventory",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "risk_summary",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "repository_summary",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "compare_scans",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_finding",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "explain_control",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "ai_governance_summary",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "992dbfc8270b1491ee143d56857417f782ac6dbb301f5ebdc707671b59117327",
  "stats": {
    "tools": 14,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 5,
      "medium": 0,
      "low": 7,
      "info": 0
    }
  }
}