Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Podcast Show Notes Mcp
v1.0.0Generate podcast show notes from audio: timestamps, topics, guest bios, key quotes, SEO summaries.
⭐ 0· 28·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
high confidencePurpose & Capability
Name/description: generate podcast show notes from audio — reasonable. But SKILL.md and README repeatedly claim '100% local AI inference (zero external API calls)' while the implementation (src/handlers/podcast.js) sends POST requests to an external NTRIQ_AI_URL (default https://ai.ntriq.co.kr). The README/DEPLOYMENT also reference Apify/Actor charging and NTRIQ endpoints. The skill therefore does not match its claim of local-only inference.
Instruction Scope
SKILL.md usage examples show curl to x402.ntriq.co.kr and describe an on-site micropay flow; the code, however, exposes an MCP server and calls external /audio/summarize and /audio/analyze endpoints. The SKILL.md omits mention of Apify Actor.charge() behavior present in code. The instructions therefore give a different runtime picture than the code — they direct network calls to endpoints and a payment flow that are not fully described or aligned with the implementation.
Install Mechanism
No install spec is provided (instruction-only), which is low-install risk. Code and package.json exist and reference standard npm packages from public registries (apify, express, @modelcontextprotocol/sdk, etc.). No unusual download URLs or arbitrary extract/install steps were found.
Credentials
Registry metadata lists no required environment variables, but the code reads NTRIQ_AI_URL (and uses APIFY_CONTAINER_PORT and relies on Apify platform credentials for Actor.charge()). The absence of declared env requirements contradicts the implementation. The skill will transmit audio to an external server (NTRIQ_AI_URL) which could leak sensitive audio if users expect local-only processing.
Persistence & Privilege
Flags: always is false and the skill does not request system-wide privileges or modify other skills. It uses autonomous invocation by default (normal). It does call Actor.charge() to bill usage, which is expected for a paid MCP actor.
What to consider before installing
Do not assume this runs locally despite the README/SKILL.md claims. The code sends audio to an external NTRIQ_AI_URL (default https://ai.ntriq.co.kr) and uses Apify charging. Before installing or using: (1) confirm with the maintainer whether inference really runs locally or if audio is sent to their servers; (2) if you require local-only processing or have sensitive audio, do not use this skill until it's verified; (3) verify where payments/charges occur (Apify Actor.charge vs. the curl/pay example to x402) and whether any wallet/auto-pay flows exist; (4) ensure you are comfortable with the external host's privacy policy and data retention; (5) request the author to declare required environment variables (NTRIQ_AI_URL, APIFY_TOKEN if applicable) in the registry metadata and to fix the contradictory documentation. If you can't confirm these points, treat the skill as untrusted and run only in an isolated/sandboxed environment.src/handlers/podcast.js:7
Environment variable access combined with network send.
Patterns worth reviewing
These patterns may indicate risky behavior. Check the VirusTotal and OpenClaw results above for context-aware analysis before installing.Like a lobster shell, security has layers — review code before you run it.
latestvk972cd4hptr4059samyn6bfjcd843fv5
License
MIT-0
Free to use, modify, and redistribute. No attribution required.