research-yt

Warn

Audited by Snyk on May 4, 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 public YouTube channel pages and video transcripts (via yt-dlp and Whisper) and instructs the agent to read the channel index JSON and per-video transcript files in ./.research-yt/ to filter, cite, and synthesize findings (see SKILL.md Steps 2–5 and scripts/list_channel.py and scripts/fetch_transcripts.py), so untrusted, user-generated web content directly influences the agent's decisions and actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 4, 2026, 12:07 PM
Issues
1