Audrey — 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": "audrey",
"source": {
"kind": "package",
"origin": "audrey"
},
"server": {
"name": "audrey"
}
},
"grade": "A",
"score": {
"score": 94,
"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": "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-1.13"
},
"capability": {
"level": "high",
"reasons": [
"can send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"code-exec",
"external-sink"
]
},
"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-002",
"title": "Shell/command execution in server code (dist/mcp-server/codex-hooks-probe.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/mcp-server/codex-hooks-probe.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/mcp-server/codex-hooks-probe.js"
},
"evidence": "rt { spawn } from 'node:child_process'; import { createInterface } from 'node:readline'; import { fileURLToPath } from '",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/mcp-server/codex-hooks-probe.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/mcp-server/index.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/mcp-server/index.js:6`): 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/mcp-server/index.js"
},
"evidence": "ecFileSync } from 'node:child_process'; import { fileURLToPath } from 'node:url'; import { parseCodexHooksListResponse }",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/mcp-server/index.js",
"line": 6,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/src/embedding.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/embedding.js:53`): 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/src/embedding.js"
},
"evidence": "const response = await fetch('https://api.openai.com/v1/embeddings', { method: 'POST',",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/src/embedding.js",
"line": 53,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/src/llm.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/llm.js:85`): 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/src/llm.js"
},
"evidence": "const response = await fetch('https://api.anthropic.com/v1/messages', { method: 'POST',",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/src/llm.js",
"line": 85,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (dist/mcp-server/index.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`dist/mcp-server/index.js:2370`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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/mcp-server/index.js"
},
"evidence": "await audrey.import(snapshot); return toolResult({ imported: true, stats: audrey.introspect() });",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "dist/mcp-server/index.js",
"line": 2370,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (dist/src/audrey.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`dist/src/audrey.js:982`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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/src/audrey.js"
},
"evidence": "is.db); } async import(snapshot) { return importMemories(this.db, this.embeddingProvider, snapshot);",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "dist/src/audrey.js",
"line": 982,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (dist/src/routes.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`dist/src/routes.js:578`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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/src/routes.js"
},
"evidence": "await audrey.import(body.snapshot); return c.json({ imported: true }); } catch (e",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "dist/src/routes.js",
"line": 578,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "memory_dream",
"tags": [],
"reasons": {}
},
{
"tool": "memory_encode",
"tags": [],
"reasons": {}
},
{
"tool": "memory_recall",
"tags": [],
"reasons": {}
},
{
"tool": "memory_consolidate",
"tags": [],
"reasons": {}
},
{
"tool": "memory_introspect",
"tags": [],
"reasons": {}
},
{
"tool": "memory_ground",
"tags": [],
"reasons": {}
},
{
"tool": "memory_resolve_truth",
"tags": [],
"reasons": {}
},
{
"tool": "memory_export",
"tags": [],
"reasons": {}
},
{
"tool": "memory_import",
"tags": [],
"reasons": {}
},
{
"tool": "memory_forget",
"tags": [],
"reasons": {}
},
{
"tool": "memory_validate",
"tags": [],
"reasons": {}
},
{
"tool": "memory_decay",
"tags": [],
"reasons": {}
},
{
"tool": "memory_status",
"tags": [],
"reasons": {}
},
{
"tool": "memory_reflect",
"tags": [],
"reasons": {}
},
{
"tool": "memory_greeting",
"tags": [],
"reasons": {}
},
{
"tool": "memory_observe_tool",
"tags": [],
"reasons": {}
},
{
"tool": "memory_recent_failures",
"tags": [],
"reasons": {}
},
{
"tool": "memory_capsule",
"tags": [],
"reasons": {}
},
{
"tool": "memory_preflight",
"tags": [],
"reasons": {}
},
{
"tool": "memory_guard_before",
"tags": [],
"reasons": {}
},
{
"tool": "memory_guard_after",
"tags": [],
"reasons": {}
},
{
"tool": "memory_reflexes",
"tags": [],
"reasons": {}
},
{
"tool": "memory_promote",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "1adade4f4601cda3a6d3747beb14ba94d8cb5e6b385bd8c27ce3894ca4a3e305",
"stats": {
"tools": 23,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 2,
"medium": 5,
"low": 0,
"info": 0
}
}
}