youtube-summarizer

Warn

Audited by Snyk on Mar 7, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and ingests transcripts from public YouTube videos via the youtube-transcript-api (see SKILL.md Step 2/3 and scripts/extract-transcript.py), and then reads that untrusted, user-generated transcript content into the AI prompt for summarization—allowing third-party text to influence the agent's outputs and behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 03:54 AM