Raw scan report

Codeplane Server Inventory — 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": "@isogonic/codeplane-server-inventory",
    "source": {
      "kind": "package",
      "origin": "@isogonic/codeplane-server-inventory"
    },
    "server": {
      "name": "@isogonic/codeplane-server-inventory"
    }
  },
  "grade": "C",
  "score": {
    "score": 73,
    "threatScore": 84,
    "grade": "C",
    "band": "C",
    "categorySubtotals": {
      "injection": 16.3,
      "exfiltration": 0,
      "permissions": 0,
      "supply-chain": 0,
      "network": 0,
      "hygiene": 0
    },
    "vector": [
      {
        "kind": "threat",
        "ruleId": "MTC-INJ-TARGET-1",
        "category": "injection",
        "severity": "high",
        "confidence": "strong",
        "rawWeight": 22,
        "confidenceMult": 0.7,
        "diminishingFactor": 1,
        "appliedPenalty": 15.4
      },
      {
        "kind": "threat",
        "ruleId": "MTC-INJ-TARGET-1",
        "category": "injection",
        "severity": "low",
        "confidence": "heuristic",
        "rawWeight": 3,
        "confidenceMult": 0.4,
        "diminishingFactor": 0.5,
        "appliedPenalty": 0.6
      },
      {
        "kind": "threat",
        "ruleId": "MTC-INJ-TARGET-1",
        "category": "injection",
        "severity": "low",
        "confidence": "heuristic",
        "rawWeight": 3,
        "confidenceMult": 0.4,
        "diminishingFactor": 0.25,
        "appliedPenalty": 0.3
      },
      {
        "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": "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": "critical",
    "reasons": [
      "ingests untrusted external content (a prompt-injection entry point)",
      "reads sensitive or local data",
      "has a read → egress path (a data-exfiltration surface)",
      "can execute shell commands or code",
      "untrusted-input, sensitive-source and egress co-exist across tools (toxic-flow surface)",
      "untrusted input can reach code execution"
    ],
    "tags": [
      "sensitive-source",
      "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 (20 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-FLOW-002",
      "title": "Completed toxic-flow trifecta across tools",
      "category": "exfiltration",
      "severity": "critical",
      "confidence": "strong",
      "description": "This server (without client built-ins) exposes a complete data-exfiltration chain: list_secrets → get_secret → exec_on. Untrusted input is ingested, private data is read, and it can be sent to an external sink via the agent composing the tools (→). Static analysis proves the primitive exists, not that a specific run will occur.",
      "remediation": "Remove one leg of the trifecta: isolate untrusted-input tools from secret-reading tools and from egress tools, or require human approval between them.",
      "location": {
        "kind": "flow",
        "name": "list_secrets → get_secret → exec_on"
      },
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "references": [],
      "data": {
        "untrusted": [
          "list_secrets"
        ],
        "sources": [
          "get_secret",
          "list_secrets"
        ],
        "sinks": [
          "exec_on"
        ],
        "path": [
          "list_secrets",
          "get_secret",
          "exec_on"
        ],
        "edges": [
          {
            "from": "list_secrets",
            "to": "get_secret",
            "kind": "agent-mediated"
          },
          {
            "from": "get_secret",
            "to": "exec_on",
            "kind": "agent-mediated"
          }
        ],
        "wired": false
      }
    },
    {
      "ruleId": "MTC-INJ-TARGET-1",
      "title": "Reference to a credential-exfiltration path in metadata",
      "category": "injection",
      "severity": "high",
      "confidence": "strong",
      "description": "Reference to a credential-exfiltration path in metadata detected in the description of tool \"validate_inventory\". Instruction-like content in tool metadata is executed by the model, not the human, and is the primary tool-poisoning vector.",
      "remediation": "Tool descriptions should describe behavior, not instruct the assistant. Treat imperative / secrecy / sequencing language in metadata as hostile.",
      "location": {
        "kind": "tool",
        "name": "validate_inventory",
        "field": "description"
      },
      "evidence": "~/.ssh",
      "owasp": "LLM01:2025 Prompt Injection",
      "data": {
        "kind": "sensitive-target"
      }
    },
    {
      "ruleId": "MTC-CAP-001",
      "title": "Tool \"exec_on\" exposes command/code execution",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "Tool \"exec_on\" appears to run shell commands or evaluate code (keyword \"exec\" 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": "exec_on"
      },
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/secrets.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/secrets.js: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": "dist/secrets.js"
      },
      "evidence": "{ execFile } from \"node:child_process\"; import { promisify } from \"node:util\"; import { homedir, platform } from \"node:o",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/secrets.js",
        "line": 28,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/ssh.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/ssh.js: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": "dist/ssh.js"
      },
      "evidence": "{ execFile } from \"node:child_process\"; import path from \"node:path\"; import { expandHome } from \"./paths.js\"; /** Map a",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/ssh.js",
        "line": 21,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-CAP-006",
      "title": "Unconstrained command parameter \"command\" on \"exec_on\"",
      "category": "permissions",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "Tool \"exec_on\" 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": "exec_on",
        "field": "inputSchema.properties.command"
      },
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "param": "command"
      }
    },
    {
      "ruleId": "MTC-CAP-005",
      "title": "Mutating tool \"exec_on\" declares no destructiveHint",
      "category": "hygiene",
      "severity": "low",
      "confidence": "heuristic",
      "description": "Tool \"exec_on\" 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": "exec_on"
      },
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-INJ-TARGET-1",
      "title": "Reference to a credential-exfiltration path in metadata",
      "category": "injection",
      "severity": "low",
      "confidence": "heuristic",
      "description": "Reference to a credential-exfiltration path in metadata detected in the description of tool \"add_server\". Instruction-like content in tool metadata is executed by the model, not the human, and is the primary tool-poisoning vector.",
      "remediation": "Tool descriptions should describe behavior, not instruct the assistant. Treat imperative / secrecy / sequencing language in metadata as hostile.",
      "location": {
        "kind": "tool",
        "name": "add_server",
        "field": "description"
      },
      "evidence": "~/.ssh",
      "owasp": "LLM01:2025 Prompt Injection",
      "data": {
        "kind": "sensitive-target"
      }
    },
    {
      "ruleId": "MTC-INJ-TARGET-1",
      "title": "Reference to a credential-exfiltration path in metadata",
      "category": "injection",
      "severity": "low",
      "confidence": "heuristic",
      "description": "Reference to a credential-exfiltration path in metadata detected in the description of tool \"paths_report\". Instruction-like content in tool metadata is executed by the model, not the human, and is the primary tool-poisoning vector.",
      "remediation": "Tool descriptions should describe behavior, not instruct the assistant. Treat imperative / secrecy / sequencing language in metadata as hostile.",
      "location": {
        "kind": "tool",
        "name": "paths_report",
        "field": "description"
      },
      "evidence": "~/.ssh",
      "owasp": "LLM01:2025 Prompt Injection",
      "data": {
        "kind": "sensitive-target"
      }
    }
  ],
  "toxicFlows": [
    {
      "id": "flow-1",
      "severity": "critical",
      "confidence": "strong",
      "untrustedInput": [
        "list_secrets"
      ],
      "sensitiveSource": [
        "get_secret",
        "list_secrets"
      ],
      "externalSink": [
        "exec_on"
      ],
      "selfContained": false,
      "path": [
        "list_secrets",
        "get_secret",
        "exec_on"
      ],
      "pathWired": false,
      "description": "A cross-tool exfiltration chain exists: list_secrets → get_secret → exec_on."
    }
  ],
  "capabilities": [
    {
      "tool": "list_servers",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_server",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_groups",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_tags",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "ssh_target_for",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "add_server",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "update_server",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "remove_server",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "inventory_info",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "paths_report",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "validate_inventory",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "secrets_info",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "set_secret",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_secret",
      "tags": [
        "sensitive-source"
      ],
      "reasons": {
        "sensitive-source": [
          "keyword \"get_secret\""
        ]
      }
    },
    {
      "tool": "list_secrets",
      "tags": [
        "untrusted-input",
        "sensitive-source"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"fetch\""
        ],
        "sensitive-source": [
          "keyword \"list_secrets\""
        ]
      }
    },
    {
      "tool": "list_all_secrets",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "delete_secret",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "audit_tail",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "ssh_check",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "exec_on",
      "tags": [
        "code-exec"
      ],
      "reasons": {
        "code-exec": [
          "keyword \"exec\" in tool name",
          "parameter \"command\""
        ]
      }
    }
  ],
  "surfaceDigest": "24fab2ba0b2150eab7f4e599272352cb647c92a00e5bcf6f40a2d9fefcafcc30",
  "stats": {
    "tools": 20,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 1,
      "high": 4,
      "medium": 1,
      "low": 3,
      "info": 0
    }
  }
}