transcribe-and-analyze

Warn

Audited by Snyk on Feb 15, 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's scripts (scripts/transcribe.py) download and transcribe media from user-supplied public URLs (e.g., YouTube via yt-dlp), and scripts/analyze_transcript.py then reads those transcripts and feeds them to an LLM for analysis, meaning the agent ingests untrusted, user-generated web content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:39 PM