Raw scan report

Sexai — 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": "sexai-mcp",
    "source": {
      "kind": "package",
      "origin": "sexai-mcp"
    },
    "server": {
      "name": "sexai-mcp"
    }
  },
  "grade": "A",
  "score": {
    "score": 92,
    "threatScore": 99,
    "grade": "A",
    "band": "A",
    "categorySubtotals": {
      "injection": 0,
      "exfiltration": 1.2,
      "permissions": 0,
      "supply-chain": 0,
      "network": 0,
      "hygiene": 0
    },
    "vector": [
      {
        "kind": "threat",
        "ruleId": "MTC-SRC-008",
        "category": "exfiltration",
        "severity": "low",
        "confidence": "heuristic",
        "rawWeight": 3,
        "confidenceMult": 0.4,
        "diminishingFactor": 1,
        "appliedPenalty": 1.2
      },
      {
        "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": [
      "ingests untrusted external content (a prompt-injection entry point)",
      "can execute shell commands or code"
    ],
    "tags": [
      "untrusted-input",
      "code-exec"
    ]
  },
  "coverage": {
    "level": "source",
    "inputs": {
      "toolSurface": true,
      "implementationSource": true,
      "packageMetadata": true,
      "liveTransport": false
    },
    "caveats": [
      "Tools were statically extracted from the published source (18 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-CAP-001",
      "title": "Tool \"publish_agent\" exposes command/code execution",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "Tool \"publish_agent\" appears to run shell commands or evaluate code (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": "publish_agent"
      },
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-CAP-001",
      "title": "Tool \"update_agent\" exposes command/code execution",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "Tool \"update_agent\" appears to run shell commands or evaluate code (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": "update_agent"
      },
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-FLOW-005",
      "title": "Untrusted input can drive an external action",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "Untrusted-input tools ([list_skills, get_private]) co-exist with external-action tools ([publish_agent, update_agent]). 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",
        "name": "list_skills → publish_agent"
      },
      "evidence": "untrusted [list_skills, get_private] → sinks [publish_agent, update_agent]",
      "owasp": "LLM06:2025 Excessive Agency",
      "references": [],
      "data": {
        "untrusted": [
          "list_skills",
          "get_private"
        ],
        "sinks": [
          "publish_agent",
          "update_agent"
        ]
      }
    },
    {
      "ruleId": "MTC-CAP-006",
      "title": "Unconstrained command parameter \"mcp_command\" on \"publish_agent\"",
      "category": "permissions",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "Tool \"publish_agent\" takes a command-shaped parameter \"mcp_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": "publish_agent",
        "field": "inputSchema.properties.mcp_command"
      },
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "param": "mcp_command"
      }
    },
    {
      "ruleId": "MTC-CAP-006",
      "title": "Unconstrained command parameter \"mcp_command\" on \"update_agent\"",
      "category": "permissions",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "Tool \"update_agent\" takes a command-shaped parameter \"mcp_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": "update_agent",
        "field": "inputSchema.properties.mcp_command"
      },
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "param": "mcp_command"
      }
    },
    {
      "ruleId": "MTC-SRC-008",
      "title": "Hardcoded JSON Web Token in server code (src/index.mjs)",
      "category": "exfiltration",
      "severity": "low",
      "confidence": "heuristic",
      "description": "A hardcoded JSON Web Token (a public-by-design (anon/publishable) key — RLS, not secrecy, protects it) appears in `src/index.mjs:21`. Verify whether this is a real credential; if so, remove and rotate it.",
      "remediation": "Remove the secret, rotate it, and load credentials from the environment or a secret store.",
      "location": {
        "kind": "server",
        "name": "src/index.mjs"
      },
      "evidence": "JSON Web Token: eyJh…(redacted)",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "secretType": "jwt",
        "file": "src/index.mjs",
        "line": 21
      }
    },
    {
      "ruleId": "MTC-CAP-005",
      "title": "Mutating tool \"publish_agent\" declares no destructiveHint",
      "category": "hygiene",
      "severity": "low",
      "confidence": "heuristic",
      "description": "Tool \"publish_agent\" 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": "publish_agent"
      },
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-CAP-005",
      "title": "Mutating tool \"update_agent\" declares no destructiveHint",
      "category": "hygiene",
      "severity": "low",
      "confidence": "heuristic",
      "description": "Tool \"update_agent\" 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": "update_agent"
      },
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    }
  ],
  "toxicFlows": [
    {
      "id": "flow-1",
      "severity": "medium",
      "confidence": "strong",
      "untrustedInput": [
        "list_skills",
        "get_private"
      ],
      "sensitiveSource": [],
      "externalSink": [
        "publish_agent",
        "update_agent"
      ],
      "selfContained": false,
      "description": "Untrusted input can drive an external action even though no sensitive source is exposed."
    }
  ],
  "capabilities": [
    {
      "tool": "list_agents",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_skills",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"browse\""
        ]
      }
    },
    {
      "tool": "get_agent",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "breed",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "publish_agent",
      "tags": [
        "code-exec"
      ],
      "reasons": {
        "code-exec": [
          "parameter \"command\""
        ]
      }
    },
    {
      "tool": "connect_agent",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "import_repo",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_private",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"download\""
        ]
      }
    },
    {
      "tool": "set_listing",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "delete_agent",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_8004_plan",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "confirm_8004",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "export_repo",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "update_agent",
      "tags": [
        "code-exec"
      ],
      "reasons": {
        "code-exec": [
          "parameter \"command\""
        ]
      }
    },
    {
      "tool": "confirm_payment",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_my_agents",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_lineage",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_payment_plan",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "3eca6929458c316eb0da1fbde58aec6c9cca50c7cc0c677e7c0591289b4c40cb",
  "stats": {
    "tools": 18,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 2,
      "medium": 3,
      "low": 3,
      "info": 0
    }
  }
}