youtube-content

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data (YouTube transcripts) which could contain malicious instructions designed to influence the agent's behavior during the transformation or summarization phase.
  • Ingestion points: Transcripts are fetched via the youtube-transcript-api in scripts/fetch_transcript.py and passed to the agent for processing.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the fetched transcript text.
  • Capability inventory: The agent uses scripts/fetch_transcript.py to get data; the script itself is limited to fetching transcripts and does not have write or execution capabilities over the host system beyond its intended function.
  • Sanitization: There is no explicit sanitization of the transcript content to remove potential injection markers before processing.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the youtube-transcript-api package. This is a well-known, standard library for the intended task and is considered a safe dependency.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 07:07 AM