Raw scan report

Coding Agents — 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": "@kadreio/mcp-coding-agents",
    "source": {
      "kind": "package",
      "origin": "@kadreio/mcp-coding-agents"
    },
    "server": {
      "name": "@kadreio/mcp-coding-agents"
    }
  },
  "grade": "C",
  "score": {
    "score": 71,
    "threatScore": 78,
    "grade": "C",
    "band": "C",
    "gateCap": "C",
    "categorySubtotals": {
      "injection": 0,
      "exfiltration": 22,
      "permissions": 0,
      "supply-chain": 0,
      "network": 0,
      "hygiene": 0
    },
    "vector": [
      {
        "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-1.13"
  },
  "capability": {
    "level": "high",
    "reasons": [
      "can execute shell commands or code"
    ],
    "tags": [
      "code-exec"
    ]
  },
  "coverage": {
    "level": "source",
    "inputs": {
      "toolSurface": true,
      "implementationSource": true,
      "packageMetadata": true,
      "liveTransport": false
    },
    "caveats": [
      "Tools were statically extracted from the published source (6 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-008",
      "title": "Hardcoded PEM private key in server code (dist/utils/self-signed-cert.js)",
      "category": "exfiltration",
      "severity": "high",
      "confidence": "confirmed",
      "description": "A hardcoded PEM private key (a live-looking credential hardcoded in shipped code) appears in `dist/utils/self-signed-cert.js:139`. 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": "dist/utils/self-signed-cert.js"
      },
      "evidence": "PEM private key: ----…(redacted)",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "secretType": "private-key",
        "file": "dist/utils/self-signed-cert.js",
        "line": 139
      }
    },
    {
      "ruleId": "MTC-CAP-001",
      "title": "Tool \"execute_command\" exposes command/code execution",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "Tool \"execute_command\" appears to run shell commands or evaluate code (keyword \"execute command\" in tool name, parameter \"command\"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.",
      "remediation": "Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.",
      "location": {
        "kind": "tool",
        "name": "execute_command"
      },
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/cli.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/cli.js: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": "dist/cli.js"
      },
      "evidence": "{ value: true }); const child_process_1 = require(\"child_process\"); const path_1 = __importDefault(require(\"path\")); con",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/cli.js",
        "line": 7,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/core/mcp-server-core.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/core/mcp-server-core.js:39`): 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": "dist/core/mcp-server-core.js"
      },
      "evidence": "l/sdk/types.js\"); const child_process_1 = require(\"child_process\"); const claude_1 = require(\"../lib/agents/claude\"); co",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/core/mcp-server-core.js",
        "line": 39,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/lib/agents/claude.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/lib/agents/claude.js:40`): 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": "dist/lib/agents/claude.js"
      },
      "evidence": "equire(\"crypto\"); const child_process_1 = require(\"child_process\"); const util_1 = require(\"util\"); const claude_code_1",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/lib/agents/claude.js",
        "line": 40,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/lib/agents/codex.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/lib/agents/codex.js: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": "dist/lib/agents/codex.js"
      },
      "evidence": "./utils/logger\"); const child_process_1 = require(\"child_process\"); const crypto_1 = require(\"crypto\"); /** * Type guar",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/lib/agents/codex.js",
        "line": 7,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/lib/agents/gemini.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/lib/agents/gemini.js: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": "dist/lib/agents/gemini.js"
      },
      "evidence": "./utils/logger\"); const child_process_1 = require(\"child_process\"); /** * Type guard to check if an object is valid Gem",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/lib/agents/gemini.js",
        "line": 7,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/mcp-server-http.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/mcp-server-http.js: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": "dist/mcp-server-http.js"
      },
      "evidence": "l/sdk/types.js\"); const child_process_1 = require(\"child_process\"); const crypto_1 = require(\"crypto\"); const dotenv_1 =",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/mcp-server-http.js",
        "line": 42,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/utils/self-signed-cert.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/utils/self-signed-cert.js:37`): 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": "dist/utils/self-signed-cert.js"
      },
      "evidence": "ignedCertificate; const child_process_1 = require(\"child_process\"); const fs = __importStar(require(\"fs\")); const path =",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/utils/self-signed-cert.js",
        "line": 37,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-CAP-006",
      "title": "Unconstrained command parameter \"command\" on \"execute_command\"",
      "category": "permissions",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "Tool \"execute_command\" takes a command-shaped parameter \"command\" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.",
      "remediation": "Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.",
      "location": {
        "kind": "tool",
        "name": "execute_command",
        "field": "inputSchema.properties.command"
      },
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "param": "command"
      }
    },
    {
      "ruleId": "MTC-CAP-005",
      "title": "Mutating tool \"execute_command\" declares no destructiveHint",
      "category": "hygiene",
      "severity": "low",
      "confidence": "heuristic",
      "description": "Tool \"execute_command\" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.",
      "remediation": "Declare accurate annotations, and gate destructive tools on user confirmation regardless.",
      "location": {
        "kind": "tool",
        "name": "execute_command"
      },
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    }
  ],
  "toxicFlows": [],
  "capabilities": [
    {
      "tool": "execute_command",
      "tags": [
        "code-exec"
      ],
      "reasons": {
        "code-exec": [
          "keyword \"execute command\" in tool name",
          "parameter \"command\""
        ]
      }
    },
    {
      "tool": "Server Configuration",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "System Statistics",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "calculate_bmi",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_timestamp",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "stream_sse_timestamps",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "4de7370c8352d5853656778e69decb4c076498f4e5b142d0d7635b19fe05fd90",
  "stats": {
    "tools": 6,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 9,
      "medium": 1,
      "low": 1,
      "info": 0
    }
  }
}