Raw scan report

Rag Reviewer — 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": "rag-reviewer",
    "source": {
      "kind": "package",
      "origin": "rag-reviewer"
    },
    "server": {
      "name": "rag-reviewer"
    }
  },
  "grade": "C",
  "score": {
    "score": 72,
    "threatScore": 83,
    "grade": "C",
    "band": "C",
    "categorySubtotals": {
      "injection": 15.4,
      "exfiltration": 0,
      "permissions": 0,
      "supply-chain": 2.1,
      "network": 0,
      "hygiene": 0
    },
    "vector": [
      {
        "kind": "threat",
        "ruleId": "MTC-SRC-004",
        "category": "injection",
        "severity": "high",
        "confidence": "strong",
        "rawWeight": 22,
        "confidenceMult": 0.7,
        "diminishingFactor": 1,
        "appliedPenalty": 15.4
      },
      {
        "kind": "threat",
        "ruleId": "MTC-SUP-011",
        "category": "supply-chain",
        "severity": "low",
        "confidence": "strong",
        "rawWeight": 3,
        "confidenceMult": 0.7,
        "diminishingFactor": 1,
        "appliedPenalty": 2.1
      },
      {
        "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 (unlocatable) — no provenance and no public repository to inspect",
        "appliedPenalty": 5
      },
      {
        "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-1.7"
  },
  "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",
      "external-sink",
      "code-exec"
    ]
  },
  "coverage": {
    "level": "source",
    "inputs": {
      "toolSurface": true,
      "implementationSource": true,
      "packageMetadata": true,
      "liveTransport": false
    },
    "caveats": [
      "Tools were statically extracted from the published source (34 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-FLOW-004",
      "title": "Sensitive-source and external-sink co-exist",
      "category": "exfiltration",
      "severity": "high",
      "confidence": "strong",
      "description": "Tools that read sensitive data ([read_file]) and tools that can send data out ([publish_review, post_pr_walkthrough]) are exposed together. An agent can move private data to the sink.",
      "remediation": "Keep secret-reading and egress capabilities on separate, separately-approved servers.",
      "location": {
        "kind": "flow"
      },
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "references": [],
      "data": {
        "sources": [
          "read_file"
        ],
        "sinks": [
          "publish_review",
          "post_pr_walkthrough"
        ]
      }
    },
    {
      "ruleId": "MTC-SRC-006",
      "title": "Reads a sensitive credential path or dumps the environment (reviewer/install_codex.py)",
      "category": "exfiltration",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`reviewer/install_codex.py:950`): 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": "reviewer/install_codex.py"
      },
      "evidence": "dict(os.environ)",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-006",
        "file": "reviewer/install_codex.py",
        "line": 950
      }
    },
    {
      "ruleId": "MTC-SRC-004",
      "title": "Obfuscated / encoded payload in server code (reviewer/graph/scip_pb2.py)",
      "category": "injection",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`reviewer/graph/scip_pb2.py:27`): Decoding an encoded blob and executing it is how malicious logic is hidden from human review of the source. 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": "reviewer/graph/scip_pb2.py"
      },
      "evidence": "\\x10\\x01\\x1a\\x02\\x08\\x01\\x12\\x08",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-004",
        "file": "reviewer/graph/scip_pb2.py",
        "line": 27
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (reviewer/entrypoints/cli.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`reviewer/entrypoints/cli.py:774`): 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": "reviewer/entrypoints/cli.py"
      },
      "evidence": "subprocess.run(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "reviewer/entrypoints/cli.py",
        "line": 774
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (reviewer/gitutil.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`reviewer/gitutil.py:8`): 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": "reviewer/gitutil.py"
      },
      "evidence": "subprocess.run(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "reviewer/gitutil.py",
        "line": 8
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (reviewer/graph/scip.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`reviewer/graph/scip.py:73`): 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": "reviewer/graph/scip.py"
      },
      "evidence": "subprocess.run(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "reviewer/graph/scip.py",
        "line": 73
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (reviewer/install_codex.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`reviewer/install_codex.py:290`): 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": "reviewer/install_codex.py"
      },
      "evidence": "subprocess.run(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "reviewer/install_codex.py",
        "line": 290
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (reviewer/services/branch.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`reviewer/services/branch.py:31`): 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": "reviewer/services/branch.py"
      },
      "evidence": "subprocess.run(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "reviewer/services/branch.py",
        "line": 31
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (tests/test_gitutil.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`tests/test_gitutil.py:6`): 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_gitutil.py"
      },
      "evidence": "subprocess.run(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "tests/test_gitutil.py",
        "line": 6
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (tests/test_infrastructure_policy.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`tests/test_infrastructure_policy.py:68`): 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_infrastructure_policy.py"
      },
      "evidence": "subprocess.run(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "tests/test_infrastructure_policy.py",
        "line": 68
      }
    },
    {
      "ruleId": "MTC-SUP-011",
      "title": "Package has no source repository",
      "category": "supply-chain",
      "severity": "low",
      "confidence": "strong",
      "description": "\"rag-reviewer\" 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": "rag-reviewer"
      }
    }
  ],
  "toxicFlows": [
    {
      "id": "flow-1",
      "severity": "high",
      "confidence": "strong",
      "untrustedInput": [],
      "sensitiveSource": [
        "read_file"
      ],
      "externalSink": [
        "publish_review",
        "post_pr_walkthrough"
      ],
      "selfContained": false,
      "path": [
        "read_file",
        "post_pr_walkthrough"
      ],
      "pathWired": false,
      "description": "A sensitive-source → external-sink chain exists: read_file → post_pr_walkthrough."
    }
  ],
  "capabilities": [
    {
      "tool": "prepare_review",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "search_code",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_related_symbols",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "read_file",
      "tags": [
        "sensitive-source"
      ],
      "reasons": {
        "sensitive-source": [
          "keyword \"read_file\""
        ]
      }
    },
    {
      "tool": "get_definition",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "find_callers",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_changed_file_diff",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_impact",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "index_task",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "index_tasks_batch",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "purge_orphaned_tasks",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "sync_board",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "finish_task",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "search_tasks",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_task_context",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_task",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "count_tasks",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_board_config",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_board_targets",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "search_codebase",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "related_symbols",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "callers",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "definition",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_pr_diff",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_subsystem_clusters",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "index_subsystem_summary",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_subsystem_summaries",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "prune_subsystem_summaries",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "backfill_summary_embeddings",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "publish_review",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"publish\""
        ]
      }
    },
    {
      "tool": "submit_findings",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "submit_verdicts",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_candidate_findings",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "post_pr_walkthrough",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"post\""
        ]
      }
    }
  ],
  "surfaceDigest": "328e53569a98846e48302a72cb36c435203a6146e43eb8239029471c5b8b72d0",
  "stats": {
    "tools": 34,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 10,
      "medium": 0,
      "low": 1,
      "info": 0
    }
  }
}