Raw scan report

Contextcore — the complete, unedited output of the deterministic mcptrustchecker engine v1.8.0, 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": "1.8.0",
    "methodologyVersion": "mcptrustchecker-1.8"
  },
  "target": {
    "id": "contextcore",
    "source": {
      "kind": "package",
      "origin": "contextcore"
    },
    "server": {
      "name": "contextcore"
    }
  },
  "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-1.8"
  },
  "capability": {
    "level": "high",
    "reasons": [
      "ingests untrusted external content (a prompt-injection entry point)",
      "reads sensitive or local data",
      "has a read → egress path (a data-exfiltration surface)",
      "can execute shell commands or code"
    ],
    "tags": [
      "untrusted-input",
      "sensitive-source",
      "code-exec"
    ]
  },
  "coverage": {
    "level": "source",
    "inputs": {
      "toolSurface": true,
      "implementationSource": true,
      "packageMetadata": true,
      "liveTransport": false
    },
    "caveats": [
      "Tools were statically extracted from the published source (16 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 (auth_manager.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`auth_manager.py:12`): 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": "auth_manager.py"
      },
      "evidence": "id4()) process = subprocess.Popen( [\"rclone\", \"authorize\", storage_type, \"--auth-no-open-browser\"],",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "auth_manager.py",
        "line": 12,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (cli/commands/cloudconnect.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`cli/commands/cloudconnect.py:77`): 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": "cli/commands/cloudconnect.py"
      },
      "evidence": "try: result = subprocess.run( [get_rclone_path()] + args, capture_output=True,",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "cli/commands/cloudconnect.py",
        "line": 77,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (cli/commands/clouddisconnect.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`cli/commands/clouddisconnect.py:36`): 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": "cli/commands/clouddisconnect.py"
      },
      "evidence": "nd(args): result = subprocess.run( [get_rclone_path()] + args, capture_output=True, text",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "cli/commands/clouddisconnect.py",
        "line": 36,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (cli/commands/doctor.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`cli/commands/doctor.py:117`): 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": "cli/commands/doctor.py"
      },
      "evidence": "extcore\"): r = subprocess.run( [sys.executable, \"-c\", \"import mcp_server\"], capture_o",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "cli/commands/doctor.py",
        "line": 117,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (cli/commands/helpers.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`cli/commands/helpers.py:251`): 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": "cli/commands/helpers.py"
      },
      "evidence": "im]\\n\") result = subprocess.run( [sys.executable, \"-m\", \"pip\", \"install\", \"--progress-bar\", \"on\", \"--no-",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "cli/commands/helpers.py",
        "line": 251,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (cli/commands/init.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`cli/commands/init.py:352`): 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": "cli/commands/init.py"
      },
      "evidence": "quiet result = subprocess.run( [sys.executable, \"-m\", \"pip\", \"install\", \"--progress-",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "cli/commands/init.py",
        "line": 352,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (cli/commands/report.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`cli/commands/report.py:44`): 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": "cli/commands/report.py"
      },
      "evidence": "try: out = subprocess.check_output( [\"git\", \"remote\", \"get-url\", \"origin\"], cwd=s",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "cli/commands/report.py",
        "line": 44,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (cli/commands/search.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`cli/commands/search.py:362`): 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": "cli/commands/search.py"
      },
      "evidence": "m == \"darwin\": subprocess.run([\"open\", path], check=True) else: subprocess.run([\"xdg-open\", path]",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "cli/commands/search.py",
        "line": 362,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (cli/commands/update.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`cli/commands/update.py:12`): 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": "cli/commands/update.py"
      },
      "evidence": "ocess[str]: return subprocess.run( [\"git\"] + args, cwd=str(cwd), capture_output=True,",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "cli/commands/update.py",
        "line": 12,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (cli/lifecycle.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`cli/lifecycle.py:59`): 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": "cli/lifecycle.py"
      },
      "evidence": ": result = subprocess.run( [\"tasklist\", \"/FI\", f\"PID eq {pid}\"], capture_",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "cli/lifecycle.py",
        "line": 59,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-005",
      "title": "Dynamic module load from a non-literal (detect_paths.py)",
      "category": "permissions",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "In the server's implementation (`detect_paths.py:200`): 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": "detect_paths.py"
      },
      "evidence": "try: __import__(dep) except Exception: missing.append(dep) if missing:",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-005",
        "file": "detect_paths.py",
        "line": 200,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-005",
      "title": "Dynamic module load from a non-literal (unimain.py)",
      "category": "permissions",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "In the server's implementation (`unimain.py:460`): 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": "unimain.py"
      },
      "evidence": "is None: mod = __import__( \"text_search_implementation_v2.search\", fromlist=[\"TextSearchEngineV2\"]",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-005",
        "file": "unimain.py",
        "line": 460,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SUP-012",
      "title": "Package has no license",
      "category": "hygiene",
      "severity": "info",
      "confidence": "strong",
      "description": "\"contextcore\" has no declared license. This is a legal/reuse concern, not a security finding.",
      "location": {
        "kind": "package",
        "name": "contextcore"
      }
    }
  ],
  "toxicFlows": [],
  "capabilities": [
    {
      "tool": "analyze_code_directory",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_codebase_context",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_codebase_index",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_module_detail",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_file_content",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "search_code_chunks",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "search",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "fetch_content",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"fetch\""
        ]
      }
    },
    {
      "tool": "list_files",
      "tags": [
        "sensitive-source"
      ],
      "reasons": {
        "sensitive-source": [
          "keyword \"list_files\""
        ]
      }
    },
    {
      "tool": "reveal_file",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "filesystem_access_profile",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "prepare_file_for_tool",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "refine_search",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_neighbors",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "index_content",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_sources",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "162a4ab6cd8ccc29bf12779803bb64aaf125bbde0ae0e43a1bc74216adb6deea",
  "stats": {
    "tools": 16,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 10,
      "medium": 2,
      "low": 0,
      "info": 1
    }
  }
}