youtube-transcript
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructions in SKILL.md use high-priority keywords ("CRITICAL: YOU MUST NEVER MODIFY...") to override standard agent behavior.
- [PROMPT_INJECTION]: The skill facilitates an indirect prompt injection attack surface by fetching untrusted text content from external YouTube transcripts and presenting it to the agent without sanitization or boundary markers.
- Ingestion points: scripts/get_transcript.py fetches data from the YouTube API via the youtube-transcript-api library.
- Boundary markers: The skill does not implement delimiters or instructions to ignore embedded commands within the fetched transcript.
- Capability inventory: The agent environment running this skill typically includes capabilities for shell execution, network access, and file system operations.
- Sanitization: No filtering or validation is performed on the transcript text before it is returned to the agent.
Audit Metadata