youtube-content-ideator
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill initiates data retrieval from several external sources including Product Hunt, Hacker News, The Verge, and TechCrunch via web search. It also utilizes the Apify platform to scrape YouTube channel metadata and video information.
- [COMMAND_EXECUTION]: The skill executes external logic through Model Context Protocol (MCP) tools, specifically triggering Apify actors (
streamers/youtube-scraper) and a PDF generation tool to create reports in thetmp/directory. - [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8) due to its data processing workflow.
- Ingestion points: Data is ingested from live web search results, social media posts from X/Twitter influencers, and competitor YouTube video titles/descriptions.
- Boundary markers: The instructions do not define clear delimiters or use 'ignore embedded instructions' warnings when the LLM processes this external content.
- Capability inventory: The skill possesses capabilities for web searching, external API calls via Apify, and file system write operations (PDF generation).
- Sanitization: There is no explicit sanitization or validation logic for the content fetched from YouTube or X/Twitter before it is used for 'Idea Generation' and 'Scoring'.
Audit Metadata