Strudel — 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": "@williamzujkowski/strudel-mcp-server",
"source": {
"kind": "package",
"origin": "@williamzujkowski/strudel-mcp-server"
},
"server": {
"name": "@williamzujkowski/strudel-mcp-server"
}
},
"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 execute shell commands or code"
],
"tags": [
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (65 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-010",
"title": "Dynamic evaluation of a non-literal value (dist/services/StrudelEngine.js)",
"category": "injection",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/services/StrudelEngine.js:130`): Evaluating a runtime value as code (rather than a fixed literal) executes whatever reaches it — a direct RCE primitive, and almost never necessary in legitimate 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/services/StrudelEngine.js"
},
"evidence": "const fn = new Function(...Object.keys(this.context), transpileResult.transpiledCode); const pa",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-010",
"file": "dist/services/StrudelEngine.js",
"line": 130,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/services/GeminiService.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/services/GeminiService.js:743`): 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/services/GeminiService.js"
},
"evidence": "or safety 7. Do not use eval(), Function(), or any dangerous constructs Return the modified pattern code:`; } /",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/services/GeminiService.js",
"line": 743,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/services/StrudelEngine.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/services/StrudelEngine.js:130`): 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/services/StrudelEngine.js"
},
"evidence": "const fn = new Function(...Object.keys(this.context), transpileResult.transpiledCode); const pa",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/services/StrudelEngine.js",
"line": 130,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/utils/PatternValidator.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/utils/PatternValidator.js:181`): 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/utils/PatternValidator.js"
},
"evidence": "errors.push('Use of eval() or Function() is not allowed'); } return { safe: errors.lengt",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/utils/PatternValidator.js",
"line": 181,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "init",
"tags": [],
"reasons": {}
},
{
"tool": "write",
"tags": [],
"reasons": {}
},
{
"tool": "append",
"tags": [],
"reasons": {}
},
{
"tool": "insert",
"tags": [],
"reasons": {}
},
{
"tool": "replace",
"tags": [],
"reasons": {}
},
{
"tool": "play",
"tags": [],
"reasons": {}
},
{
"tool": "pause",
"tags": [],
"reasons": {}
},
{
"tool": "stop",
"tags": [],
"reasons": {}
},
{
"tool": "clear",
"tags": [],
"reasons": {}
},
{
"tool": "get_pattern",
"tags": [],
"reasons": {}
},
{
"tool": "transpose",
"tags": [],
"reasons": {}
},
{
"tool": "reverse",
"tags": [],
"reasons": {}
},
{
"tool": "stretch",
"tags": [],
"reasons": {}
},
{
"tool": "quantize",
"tags": [],
"reasons": {}
},
{
"tool": "humanize",
"tags": [],
"reasons": {}
},
{
"tool": "generate_variation",
"tags": [],
"reasons": {}
},
{
"tool": "generate_pattern",
"tags": [],
"reasons": {}
},
{
"tool": "generate_drums",
"tags": [],
"reasons": {}
},
{
"tool": "generate_bassline",
"tags": [],
"reasons": {}
},
{
"tool": "generate_melody",
"tags": [],
"reasons": {}
},
{
"tool": "analyze",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_spectrum",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_rhythm",
"tags": [],
"reasons": {}
},
{
"tool": "detect_tempo",
"tags": [],
"reasons": {}
},
{
"tool": "detect_key",
"tags": [],
"reasons": {}
},
{
"tool": "validate_pattern_runtime",
"tags": [],
"reasons": {}
},
{
"tool": "add_effect",
"tags": [],
"reasons": {}
},
{
"tool": "remove_effect",
"tags": [],
"reasons": {}
},
{
"tool": "set_tempo",
"tags": [],
"reasons": {}
},
{
"tool": "add_swing",
"tags": [],
"reasons": {}
},
{
"tool": "apply_scale",
"tags": [],
"reasons": {}
},
{
"tool": "shift_mood",
"tags": [],
"reasons": {}
},
{
"tool": "save",
"tags": [],
"reasons": {}
},
{
"tool": "load",
"tags": [],
"reasons": {}
},
{
"tool": "list",
"tags": [],
"reasons": {}
},
{
"tool": "undo",
"tags": [],
"reasons": {}
},
{
"tool": "redo",
"tags": [],
"reasons": {}
},
{
"tool": "list_history",
"tags": [],
"reasons": {}
},
{
"tool": "restore_history",
"tags": [],
"reasons": {}
},
{
"tool": "compare_patterns",
"tags": [],
"reasons": {}
},
{
"tool": "generate_scale",
"tags": [],
"reasons": {}
},
{
"tool": "generate_chord_progression",
"tags": [],
"reasons": {}
},
{
"tool": "generate_euclidean",
"tags": [],
"reasons": {}
},
{
"tool": "generate_polyrhythm",
"tags": [],
"reasons": {}
},
{
"tool": "generate_fill",
"tags": [],
"reasons": {}
},
{
"tool": "performance_report",
"tags": [],
"reasons": {}
},
{
"tool": "memory_usage",
"tags": [],
"reasons": {}
},
{
"tool": "show_browser",
"tags": [],
"reasons": {}
},
{
"tool": "screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "status",
"tags": [],
"reasons": {}
},
{
"tool": "diagnostics",
"tags": [],
"reasons": {}
},
{
"tool": "show_errors",
"tags": [],
"reasons": {}
},
{
"tool": "compose",
"tags": [],
"reasons": {}
},
{
"tool": "get_pattern_feedback",
"tags": [],
"reasons": {}
},
{
"tool": "start_audio_capture",
"tags": [],
"reasons": {}
},
{
"tool": "stop_audio_capture",
"tags": [],
"reasons": {}
},
{
"tool": "capture_audio_sample",
"tags": [],
"reasons": {}
},
{
"tool": "export_midi",
"tags": [],
"reasons": {}
},
{
"tool": "create_session",
"tags": [],
"reasons": {}
},
{
"tool": "destroy_session",
"tags": [],
"reasons": {}
},
{
"tool": "list_sessions",
"tags": [],
"reasons": {}
},
{
"tool": "switch_session",
"tags": [],
"reasons": {}
},
{
"tool": "refine",
"tags": [],
"reasons": {}
},
{
"tool": "set_energy",
"tags": [],
"reasons": {}
},
{
"tool": "jam_with",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "e54907990bdcfc767ff7e99d186d03785e5eeef262c26dbfe25c9f7944d76edf",
"stats": {
"tools": 65,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 4,
"medium": 0,
"low": 0,
"info": 0
}
}
}