youtube-transcript

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the 'youtube-transcript-api' package from the official Python Package Index (PyPI). This is a well-known and standard library for the stated purpose of transcript retrieval.
  • [PROMPT_INJECTION]: As the skill retrieves and processes untrusted content from external sources (YouTube video captions), it has an inherent surface for indirect prompt injection.
  • Ingestion points: Transcript data is fetched in youtube_transcript_tool.py using the youtube-transcript-api dependency.
  • Boundary markers: The skill relies on structured JSON output for tool results, but does not implement specific text-based delimiters for the transcript content itself.
  • Capability inventory: The script is limited to data processing and does not perform file-system modifications, network exfiltration, or secondary subprocess execution.
  • Sanitization: The script performs tokenization and stopword removal for its analysis modes, though the raw transcript is passed back to the agent for summarization. This risk is common to all content-retrieval tools and is considered low-impact in this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 11:21 PM