Raw scan report

Fs Git — 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": "fs-git-mcp",
    "source": {
      "kind": "package",
      "origin": "fs-git-mcp"
    },
    "server": {
      "name": "fs-git-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": [
      "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"
    ]
  },
  "coverage": {
    "level": "source",
    "inputs": {
      "toolSurface": true,
      "implementationSource": true,
      "packageMetadata": true,
      "liveTransport": false
    },
    "caveats": [
      "Tools were statically extracted from the published source (28 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 (debug_mcp_methods.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`debug_mcp_methods.py:17`): 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": "debug_mcp_methods.py"
      },
      "evidence": "rver process proc = subprocess.Popen( [sys.executable, \"mcp_server/server_fastmcp_new.py\"], stdin=su",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "debug_mcp_methods.py",
        "line": 17,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (mcp_server/cli/main.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`mcp_server/cli/main.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": "mcp_server/cli/main.py"
      },
      "evidence": "Initialize git repo subprocess.run([\"git\", \"init\", repo_root], check=True) # Set safe.directory subprocess.",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "mcp_server/cli/main.py",
        "line": 42,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (mcp_server/git_backend/commits.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`mcp_server/git_backend/commits.py:22`): 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": "mcp_server/git_backend/commits.py"
      },
      "evidence": "try: result = subprocess.run( [\"git\", \"-C\", repo.root, \"log\", f\"--oneline\", f\"-{window}\", \"--forma",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "mcp_server/git_backend/commits.py",
        "line": 22,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (mcp_server/git_backend/history.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`mcp_server/git_backend/history.py:7`): 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": "mcp_server/git_backend/history.py"
      },
      "evidence": "try: result = subprocess.run( [\"git\", \"-C\", repo.root, \"log\", f\"--oneline\", f\"-{limit}\", \"--\", pat",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "mcp_server/git_backend/history.py",
        "line": 7,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (mcp_server/git_backend/repo.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`mcp_server/git_backend/repo.py:17`): 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": "mcp_server/git_backend/repo.py"
      },
      "evidence": "safe.directory subprocess.run([\"git\", \"config\", \"--global\", \"--add\", \"safe.directory\", self.root], check=True)",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "mcp_server/git_backend/repo.py",
        "line": 17,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (mcp_server/git_backend/safety.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`mcp_server/git_backend/safety.py:85`): 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": "mcp_server/git_backend/safety.py"
      },
      "evidence": "try: result = subprocess.run([\"git\", \"-C\", repo.root, \"status\", \"--porcelain\"], capture_output=True, text=True",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "mcp_server/git_backend/safety.py",
        "line": 85,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (mcp_server/git_backend/staging.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`mcp_server/git_backend/staging.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": "mcp_server/git_backend/staging.py"
      },
      "evidence": "log_result = subprocess.run( [\"git\", \"-C\", self.repo.root, \"log\", \"--oneline\", f\"{self.base_b",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "mcp_server/git_backend/staging.py",
        "line": 21,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (mcp_server/git_backend/templates.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`mcp_server/git_backend/templates.py:41`): 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": "mcp_server/git_backend/templates.py"
      },
      "evidence": "try: result = subprocess.run( ['git', 'log', f'--oneline', f'-{window}', '--format=%s'],",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "mcp_server/git_backend/templates.py",
        "line": 41,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-CAP-008",
      "title": "Unconstrained path parameter \"path\" on \"read_with_history\"",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "Tool \"read_with_history\" takes a path parameter \"path\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
      "remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
      "location": {
        "kind": "tool",
        "name": "read_with_history",
        "field": "inputSchema.properties.path"
      },
      "data": {
        "param": "path"
      }
    },
    {
      "ruleId": "MTC-CAP-008",
      "title": "Unconstrained path parameter \"path\" on \"read_file\"",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "Tool \"read_file\" takes a path parameter \"path\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
      "remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
      "location": {
        "kind": "tool",
        "name": "read_file",
        "field": "inputSchema.properties.path"
      },
      "data": {
        "param": "path"
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in packaging/dev tooling (basic_mcp_test.py)",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`basic_mcp_test.py:15`): 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": "basic_mcp_test.py"
      },
      "evidence": "h): self.proc = subprocess.Popen( [sys.executable, server_path], stdin=subprocess.PIPE,",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "basic_mcp_test.py",
        "line": 15,
        "nonRuntime": true
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in packaging/dev tooling (comprehensive_mcp_test.py)",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`comprehensive_mcp_test.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": "comprehensive_mcp_test.py"
      },
      "evidence": "h): self.proc = subprocess.Popen( [sys.executable, server_path], stdin=subprocess.PIPE,",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "comprehensive_mcp_test.py",
        "line": 16,
        "nonRuntime": true
      }
    }
  ],
  "toxicFlows": [],
  "capabilities": [
    {
      "tool": "write_and_commit",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "read_with_history",
      "tags": [
        "sensitive-source"
      ],
      "reasons": {
        "sensitive-source": [
          "keyword \"read_file\""
        ]
      }
    },
    {
      "tool": "start_staged",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "staged_write",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "staged_preview",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "finalize_staged",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "abort_staged",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "lint_commit_message",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "extract",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "answer_about_file",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "replace_and_commit_func",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "batch_replace_and_commit_func",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "preview_diff_func",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "apply_patch_and_commit_func",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "read_file_func",
      "tags": [
        "sensitive-source"
      ],
      "reasons": {
        "sensitive-source": [
          "keyword \"read_file\""
        ]
      }
    },
    {
      "tool": "stat_file_func",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_dir_func",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "make_dir_func",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "replace_and_commit",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "preview_diff",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "read_file",
      "tags": [
        "sensitive-source"
      ],
      "reasons": {
        "sensitive-source": [
          "keyword \"read_file\""
        ]
      }
    },
    {
      "tool": "batch_replace_and_commit",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "apply_patch_and_commit",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "stat_file",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_dir",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "make_dir",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "add",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "test_add",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "3aae1e10750a1db96f0f9a7bd84c823efc3a0e2fc62400e91bd66f79ce59ce6e",
  "stats": {
    "tools": 28,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 8,
      "medium": 0,
      "low": 4,
      "info": 0
    }
  }
}