youtube-video-analyzer
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection attacks because it ingests and processes untrusted data from external sources.
- Ingestion points: Data is fetched from YouTube video pages (titles, descriptions) and third-party transcript services (youtubetranscript.com).
- Boundary markers: None. The skill does not define clear delimiters or instructions to the AI to ignore embedded commands within the fetched content.
- Capability inventory: The agent has access to
Read/Writetools for caching results andWebFetchfor network requests. - Sanitization: None. There is no evidence of validation or filtering for the external text before it is analyzed by the AI.
- [EXTERNAL_DOWNLOADS]: The skill performs network operations to retrieve video data and transcripts from external domains.
- Evidence: Fetches content from
youtube.comandyoutubetranscript.comusing theWebFetchtool. - Context: These operations are required for the primary function of the skill, but users should be aware that content is being pulled from a third-party transcription service.
Audit Metadata