Bob Control — 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.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.13.0",
"methodologyVersion": "mcptrustchecker-1.13"
},
"target": {
"id": "@pounceai/bob-control",
"source": {
"kind": "package",
"origin": "@pounceai/bob-control"
},
"server": {
"name": "@pounceai/bob-control"
}
},
"grade": "B",
"score": {
"score": 83,
"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": "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": "critical",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can execute shell commands or code",
"untrusted input can reach code execution"
],
"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 (23 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 (dist/command-policy.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/command-policy.js:96`): 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": "dist/command-policy.js"
},
"evidence": "\\b/i, why: \"node inline eval (-e/-p)\" }, { re: /\\bnode\\b[^|&;\\n]*\\s--(eval|print)\\b/i, why: \"node inline eval (--eva",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/command-policy.js",
"line": 96,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/bob-polls.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/bob-polls.js:8`): 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/bob-polls.js"
},
"evidence": "rt { spawn } from \"node:child_process\"; import { snapshotWorktreeTreeBounded } from \"./git.js\"; /** * Run the verificat",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/bob-polls.js",
"line": 8,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/git.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/git.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/git.js"
},
"evidence": "rt { spawn } from \"node:child_process\"; import { resolve } from \"node:path\"; import { rmSync } from \"node:fs\"; /** * Ru",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/git.js",
"line": 4,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/llm.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/llm.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/llm.js"
},
"evidence": "nodeSpawn } from \"node:child_process\"; export const DEFAULT_MODELS = { api: \"claude-haiku-4-5\", cli: \"claude-so",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/llm.js",
"line": 7,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/notify.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/notify.js:1`): 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/notify.js"
},
"evidence": "rt { spawn } from \"node:child_process\"; // Fire-and-forget desktop notification. On Windows, optionally plays a system /",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/notify.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (dist/llm.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/llm.js:88`): 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/llm.js"
},
"evidence": "\" ? spawn(`\"${cli}\" ${argv.join(\" \")}`, { shell: true, stdio: [\"pipe\", \"pipe\", \"pipe\"] })",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "dist/llm.js",
"line": 88,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "create_task",
"tags": [],
"reasons": {}
},
{
"tool": "list_tasks",
"tags": [],
"reasons": {}
},
{
"tool": "get_task",
"tags": [],
"reasons": {}
},
{
"tool": "get_next_task",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "predict_mode",
"tags": [],
"reasons": {}
},
{
"tool": "claim_task",
"tags": [],
"reasons": {}
},
{
"tool": "update_task_status",
"tags": [],
"reasons": {}
},
{
"tool": "add_task_note",
"tags": [],
"reasons": {}
},
{
"tool": "submit_result",
"tags": [],
"reasons": {}
},
{
"tool": "ask_question",
"tags": [],
"reasons": {}
},
{
"tool": "answer_task_question",
"tags": [],
"reasons": {}
},
{
"tool": "await_answer",
"tags": [],
"reasons": {}
},
{
"tool": "await_task",
"tags": [],
"reasons": {}
},
{
"tool": "set_task_mode",
"tags": [],
"reasons": {}
},
{
"tool": "set_task_dependencies",
"tags": [],
"reasons": {}
},
{
"tool": "delete_task",
"tags": [],
"reasons": {}
},
{
"tool": "disarm_board",
"tags": [],
"reasons": {}
},
{
"tool": "arm_board",
"tags": [],
"reasons": {}
},
{
"tool": "release_tasks",
"tags": [],
"reasons": {}
},
{
"tool": "board_status",
"tags": [],
"reasons": {}
},
{
"tool": "record_artifact",
"tags": [],
"reasons": {}
},
{
"tool": "board_report",
"tags": [],
"reasons": {}
},
{
"tool": "revert_task",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "19bbf4def4b5155c8cf5c8a853ac9ff197647bc90ce1cadf201edf54bdae1a65",
"stats": {
"tools": 23,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 5,
"medium": 1,
"low": 0,
"info": 0
}
}
}