Youtube Mcp Tools — the complete, unedited output of the deterministic mcptrustchecker engine v1.8.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.8.0",
"methodologyVersion": "mcptrustchecker-1.8"
},
"target": {
"id": "youtube-mcp-tools",
"source": {
"kind": "package",
"origin": "youtube-mcp-tools"
},
"server": {
"name": "youtube-mcp-tools"
}
},
"grade": "C",
"score": {
"score": 74,
"threatScore": 78,
"grade": "C",
"band": "C",
"gateCap": "C",
"categorySubtotals": {
"injection": 0,
"exfiltration": 22,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SRC-008",
"category": "exfiltration",
"severity": "high",
"confidence": "confirmed",
"rawWeight": 22,
"confidenceMult": 1,
"diminishingFactor": 1,
"appliedPenalty": 22
},
{
"kind": "client",
"term": "capability-exposure",
"level": "moderate",
"label": "capability blast radius (moderate) — client exposure if the model is manipulated",
"appliedPenalty": 3
},
{
"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": [
"1 confirmed high finding → grade capped at C"
],
"methodologyVersion": "mcptrustchecker-1.8"
},
"capability": {
"level": "moderate",
"reasons": [
"can send data / act on an external service"
],
"tags": [
"external-sink"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (38 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-008",
"title": "Hardcoded Google API key in server code (dist/youtube/transcript.js)",
"category": "exfiltration",
"severity": "high",
"confidence": "confirmed",
"description": "A live-looking Google API key is hardcoded in `dist/youtube/transcript.js:14`. Secrets in source ship to everyone who installs the package and are a direct credential leak.",
"remediation": "Remove the secret, rotate it, and load credentials from the environment or a secret store.",
"location": {
"kind": "server",
"name": "dist/youtube/transcript.js"
},
"evidence": "Google API key: AIza…(redacted)",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"secretType": "google-api-key",
"file": "dist/youtube/transcript.js",
"line": 14
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/intelligence/embeddings.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/intelligence/embeddings.js:132`): 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/intelligence/embeddings.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/intelligence/embeddings.js",
"line": 132,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/youtube/transcript.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/youtube/transcript.js:74`): 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/youtube/transcript.js"
},
"evidence": "playerResponse = await fetch(`https://www.youtube.com/youtubei/v1/player?key=${this.innertubeKey}`, { metho",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/youtube/transcript.js",
"line": 74,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "youtube_search",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_video_details",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_video_list",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_channel",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_playlist",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_comments",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_trending",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_categories",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_transcript",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_transcript_search",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_related",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_channel_videos",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_channel_popular",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_live",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_search_date_range",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_compare",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_channel_analytics",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_video_summary",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_analyze",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_extract_concepts",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_research",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_compare_approaches",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_chunk_transcript",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_get_chunk",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_cache_stats",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_generate_flashcards",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_generate_quiz",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_study_guide",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_generate_learning_path",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_repurpose_content",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_analyze_watch_history",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_analyze_content_gaps",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_embed_video",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_semantic_search",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_find_similar",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_cluster_videos",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_semantic_stats",
"tags": [],
"reasons": {}
},
{
"tool": "youtube_preferences",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "4a48e07f4ae26a5e8866ce9adbb3b14318a988fd6ca8888427ba488899295b41",
"stats": {
"tools": 38,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 1,
"medium": 2,
"low": 0,
"info": 0
}
}
}