youtube-transcript

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads the youtube-transcript-plus package from the official npm registry during the installation phase.
  • [PROMPT_INJECTION]: The skill processes untrusted transcript data from YouTube, which presents a surface for indirect prompt injection.
  • Ingestion points: transcript.js fetches transcript text from the YouTube API using the youtube-transcript-plus library.
  • Boundary markers: No delimiters or protective instructions are used to isolate the fetched content in the output.
  • Capability inventory: Analysis of transcript.js shows no dangerous operations such as shell command execution, file system writes, or exfiltration of sensitive local data.
  • Sanitization: Transcript content is printed directly as retrieved without sanitization or filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 08:26 PM
Security Audit — agent-trust-hub — youtube-transcript