Raw scan report

Vectora Agent — 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": "vectora-agent",
    "source": {
      "kind": "package",
      "origin": "vectora-agent"
    },
    "server": {
      "name": "vectora-agent"
    }
  },
  "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": [
      "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 (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-006",
      "title": "Reads a sensitive credential path or dumps the environment (vectora/services/ignore_validator.py)",
      "category": "exfiltration",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`vectora/services/ignore_validator.py:74`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. 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": "vectora/services/ignore_validator.py"
      },
      "evidence": "\".jks\", \"id_rsa\", \"id_ed25519\", \".ssh\", \".aws\", \".kube\",",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-006",
        "file": "vectora/services/ignore_validator.py",
        "line": 74,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (check_coverage.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`check_coverage.py:38`): 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": "check_coverage.py"
      },
      "evidence": "int(\"=\" * 60) result = subprocess.run(cmd, capture_output=True, text=True) # Extrair output output_lines = result.stdo",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "check_coverage.py",
        "line": 38,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (run_coverage.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`run_coverage.py:46`): 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": "run_coverage.py"
      },
      "evidence": ") # Executar result = subprocess.run(cmd, cwd=\"/home/user/vectora\") sys.exit(result.returncode)",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "run_coverage.py",
        "line": 46,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (vectora/ui/chat.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`vectora/ui/chat.py:139`): 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": "vectora/ui/chat.py"
      },
      "evidence": "import os os.system(\"cls\" if os.name == \"nt\" else \"clear\") # noqa: S605 ASYNC221 try:",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "vectora/ui/chat.py",
        "line": 139,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in packaging/dev tooling (tests/e2e/test_gemini_cli.py)",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/e2e/test_gemini_cli.py:42`): 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/e2e/test_gemini_cli.py"
      },
      "evidence": "try: result = subprocess.run( [\"gemini\", \"--version\"], capture_output=True,",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "tests/e2e/test_gemini_cli.py",
        "line": 42,
        "nonRuntime": true
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in packaging/dev tooling (tests/integration/test_mcp_tools.py)",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/integration/test_mcp_tools.py:328`): 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/integration/test_mcp_tools.py"
      },
      "evidence": "try: proc = subprocess.Popen( vectora_mcp_command, stdin=subprocess.PIPE,",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "tests/integration/test_mcp_tools.py",
        "line": 328,
        "nonRuntime": true
      }
    },
    {
      "ruleId": "MTC-SUP-011",
      "title": "Package declares no source repository",
      "category": "supply-chain",
      "severity": "info",
      "confidence": "strong",
      "description": "\"vectora-agent\" 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": "vectora-agent"
      }
    }
  ],
  "toxicFlows": [],
  "capabilities": [
    {
      "tool": "web_search_tool",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"web_search\""
        ]
      }
    },
    {
      "tool": "fetch_url_tool",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"fetch_url\""
        ]
      }
    },
    {
      "tool": "vector_search_tool",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "embedding_tool",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "ingest_docs_tool",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "manage_retriever_tool",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "file_read_tool",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "file_edit_tool",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "file_write_tool",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "grep_tool",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_dir_tool",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "terminal_tool",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "call_mcp_tool_tool",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "delegate_task_to_vectora",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "627536c07b7c8f560d806050e91db031c681a810625c93fd2150bbc7adab02fa",
  "stats": {
    "tools": 14,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 4,
      "medium": 0,
      "low": 2,
      "info": 1
    }
  }
}