Raw scan report

Loom 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": "loom-agent",
    "source": {
      "kind": "package",
      "origin": "loom-agent"
    },
    "server": {
      "name": "loom-agent"
    }
  },
  "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-1.9"
  },
  "capability": {
    "level": "high",
    "reasons": [
      "can execute shell commands or code"
    ],
    "tags": [
      "code-exec"
    ]
  },
  "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-002",
      "title": "Shell/command execution in server code (loom/ecosystem/mcp.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`loom/ecosystem/mcp.py:149`): 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": "loom/ecosystem/mcp.py"
      },
      "evidence": "or {})} proc = subprocess.Popen( cmd, stdin=subprocess.PIPE, stdout=subproc",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "loom/ecosystem/mcp.py",
        "line": 149,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (loom/experimental/cluster/fork.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`loom/experimental/cluster/fork.py:28`): 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": "loom/experimental/cluster/fork.py"
      },
      "evidence": "self.max_depth def spawn(self, config: SubAgentConfig) -> str: \"\"\"Spawn 子 Agent\"\"\" if not self.can_",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "loom/experimental/cluster/fork.py",
        "line": 28,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (loom/orchestration/coordinator.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`loom/orchestration/coordinator.py:99`): 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": "loom/orchestration/coordinator.py"
      },
      "evidence": "t provide delegate() or spawn()\") coro = spawn( request.goal, depth=request.depth,",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "loom/orchestration/coordinator.py",
        "line": 99,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (loom/orchestration/subagent.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`loom/orchestration/subagent.py:20`): 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": "loom/orchestration/subagent.py"
      },
      "evidence": "ny] = [] async def spawn(self, goal: str, depth: int, inherit_context: bool = True) -> SubAgentResult: \"\"\"S",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "loom/orchestration/subagent.py",
        "line": 20,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (loom/runtime/delegation.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`loom/runtime/delegation.py:124`): 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": "loom/runtime/delegation.py"
      },
      "evidence": "on manager must provide spawn()\") coro = spawn( request.goal, depth=request.depth,",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "loom/runtime/delegation.py",
        "line": 124,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (loom/tools/builtin/shell_operations.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`loom/tools/builtin/shell_operations.py:13`): 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": "loom/tools/builtin/shell_operations.py"
      },
      "evidence": "syncio.subprocess.PIPE, shell=True ) stdout, stderr = await asyncio.wait_for(proc.communicate(), timeou",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "loom/tools/builtin/shell_operations.py",
        "line": 13,
        "nonRuntime": false
      }
    }
  ],
  "toxicFlows": [],
  "capabilities": [],
  "surfaceDigest": "f5874c8d072d44580c39bf571e975a72fd7610778b9bfeb11f4e3d40ecdcedb0",
  "stats": {
    "tools": 0,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 6,
      "medium": 0,
      "low": 0,
      "info": 0
    }
  }
}