Raw scan report

Agentchannel — 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": "agentchannel",
    "source": {
      "kind": "package",
      "origin": "agentchannel"
    },
    "server": {
      "name": "agentchannel"
    }
  },
  "grade": "B",
  "score": {
    "score": 84,
    "threatScore": 94,
    "grade": "B",
    "band": "B",
    "categorySubtotals": {
      "injection": 6.3,
      "exfiltration": 0,
      "permissions": 0,
      "supply-chain": 0,
      "network": 0,
      "hygiene": 0
    },
    "vector": [
      {
        "kind": "threat",
        "ruleId": "MTC-SRC-009",
        "category": "injection",
        "severity": "medium",
        "confidence": "strong",
        "rawWeight": 9,
        "confidenceMult": 0.7,
        "diminishingFactor": 1,
        "appliedPenalty": 6.3
      },
      {
        "kind": "client",
        "term": "capability-exposure",
        "level": "critical",
        "label": "capability blast radius (critical) — client exposure if the model is manipulated",
        "appliedPenalty": 10
      },
      {
        "kind": "client",
        "term": "verification-discount",
        "level": "source",
        "label": "publisher verification (provenance) — cryptographic build provenance ties the artifact to its source",
        "appliedPenalty": 0
      },
      {
        "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": "critical",
    "reasons": [
      "ingests untrusted external content (a prompt-injection entry point)",
      "can send data / act on an external service",
      "can execute shell commands or code",
      "untrusted input can reach code execution"
    ],
    "tags": [
      "untrusted-input",
      "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 (32 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-001",
      "title": "Dynamic code execution in server code (ui/mqtt.min.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`ui/mqtt.min.js:3`): 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": "ui/mqtt.min.js"
      },
      "evidence": "Function(\"",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-001",
        "file": "ui/mqtt.min.js",
        "line": 3
      }
    },
    {
      "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:571`): 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": "child_process",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/cli.js",
        "line": 571
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/mqtt-client.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/mqtt-client.js:4`): 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/mqtt-client.js"
      },
      "evidence": "child_process",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/mqtt-client.js",
        "line": 4
      }
    },
    {
      "ruleId": "MTC-FLOW-005",
      "title": "Untrusted input can drive an external action",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "Untrusted-input tools ([get_message, read_messages]) co-exist with external-action tools ([create_webhook, create_handoff, delete_hook, publish_channel, send_message]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.",
      "remediation": "Require confirmation for state-changing/egress actions triggered after processing untrusted content.",
      "location": {
        "kind": "flow"
      },
      "owasp": "LLM06:2025 Excessive Agency",
      "references": [],
      "data": {
        "untrusted": [
          "get_message",
          "read_messages"
        ],
        "sinks": [
          "create_webhook",
          "create_handoff",
          "delete_hook",
          "publish_channel",
          "send_message"
        ]
      }
    },
    {
      "ruleId": "MTC-SRC-003",
      "title": "Hardcoded egress to an external endpoint (dist/cli.js)",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/cli.js:165`): 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": "dist/cli.js"
      },
      "evidence": "fetch(`https://api.agentchannel.workers.dev/invites?token=${opts.token}`",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-003",
        "file": "dist/cli.js",
        "line": 165
      }
    },
    {
      "ruleId": "MTC-SRC-003",
      "title": "Hardcoded egress to an external endpoint (dist/server.js)",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/server.js:34`): 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": "dist/server.js"
      },
      "evidence": "fetch(\"https://registry.npmjs.org/agentchannel/latest\"",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-003",
        "file": "dist/server.js",
        "line": 34
      }
    },
    {
      "ruleId": "MTC-SRC-003",
      "title": "Hardcoded egress to an external endpoint (dist/tools/create.js)",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/tools/create.js:31`): 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": "dist/tools/create.js"
      },
      "evidence": "fetch(\"https://api.agentchannel.workers.dev/invites\"",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-003",
        "file": "dist/tools/create.js",
        "line": 31
      }
    },
    {
      "ruleId": "MTC-SRC-003",
      "title": "Hardcoded egress to an external endpoint (dist/tools/registry.js)",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/tools/registry.js:27`): 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": "dist/tools/registry.js"
      },
      "evidence": "fetch(\"https://api.agentchannel.workers.dev/invites\"",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-003",
        "file": "dist/tools/registry.js",
        "line": 27
      }
    },
    {
      "ruleId": "MTC-SRC-003",
      "title": "Hardcoded egress to an external endpoint (dist/update-check.js)",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/update-check.js:49`): 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": "dist/update-check.js"
      },
      "evidence": "fetch(\"https://registry.npmjs.org/agentchannel/latest\"",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-003",
        "file": "dist/update-check.js",
        "line": 49
      }
    },
    {
      "ruleId": "MTC-SRC-003",
      "title": "Hardcoded egress to an external endpoint (ui/app.js)",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "In the server's implementation (`ui/app.js:713`): 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": "ui/app.js"
      },
      "evidence": "fetch(\"https://api.agentchannel.workers.dev/invites\"",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-003",
        "file": "ui/app.js",
        "line": 713
      }
    },
    {
      "ruleId": "MTC-SRC-009",
      "title": "Untrusted input concatenated into a command sink (dist/cli.js)",
      "category": "injection",
      "severity": "medium",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/cli.js:572`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. 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": "exec(`open http://localhost:${",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-009",
        "file": "dist/cli.js",
        "line": 572
      }
    },
    {
      "ruleId": "MTC-CAP-007",
      "title": "Unconstrained URL/host parameter \"url\" on \"create_webhook\"",
      "category": "network",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "Tool \"create_webhook\" takes a URL/host parameter \"url\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
      "remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
      "location": {
        "kind": "tool",
        "name": "create_webhook",
        "field": "inputSchema.properties.url"
      },
      "owasp": "LLM06:2025 Excessive Agency",
      "data": {
        "param": "url"
      }
    },
    {
      "ruleId": "MTC-CAP-007",
      "title": "Unconstrained URL/host parameter \"url\" on \"create_handoff\"",
      "category": "network",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "Tool \"create_handoff\" takes a URL/host parameter \"url\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
      "remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
      "location": {
        "kind": "tool",
        "name": "create_handoff",
        "field": "inputSchema.properties.url"
      },
      "owasp": "LLM06:2025 Excessive Agency",
      "data": {
        "param": "url"
      }
    }
  ],
  "toxicFlows": [
    {
      "id": "flow-1",
      "severity": "medium",
      "confidence": "strong",
      "untrustedInput": [
        "get_message",
        "read_messages"
      ],
      "sensitiveSource": [],
      "externalSink": [
        "create_webhook",
        "create_handoff",
        "delete_hook",
        "publish_channel",
        "send_message"
      ],
      "selfContained": false,
      "description": "Untrusted input can drive an external action even though no sensitive source is exposed."
    }
  ],
  "capabilities": [
    {
      "tool": "brain_query",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "brain_recent",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "brain_decide",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "brain_status",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "join_channel",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "leave_channel",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_channels",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "create_channel",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "send_dm",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_message",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"read_message\""
        ]
      }
    },
    {
      "tool": "create_webhook",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"post\"",
          "parameter \"url\""
        ]
      }
    },
    {
      "tool": "create_handoff",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"post\"",
          "parameter \"url\""
        ]
      }
    },
    {
      "tool": "list_hooks",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "delete_hook",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"webhook\""
        ]
      }
    },
    {
      "tool": "get_identity",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_channel_info",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "remove_member",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "rotate_channel",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_members",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mute_channel",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "unmute_channel",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "set_name",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "read_messages",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"read_message\""
        ]
      }
    },
    {
      "tool": "publish_channel",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"publish\""
        ]
      }
    },
    {
      "tool": "search_channels",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "unpublish_channel",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "retract_message",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "send_message",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"send_message\""
        ]
      }
    },
    {
      "tool": "add_subchannel",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "remove_subchannel",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "unread_count",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "set_channel",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "501b18987140ed62cdfdfd514a78ea8f3463ec0ee1e0f7e32bf1a7240e3bc12e",
  "stats": {
    "tools": 32,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 3,
      "medium": 10,
      "low": 0,
      "info": 0
    }
  }
}