youtube-podcast-extraction

Warn

Audited by Snyk on Apr 9, 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 downloads and ingests open web content—YouTube videos and VTT subtitles via yt-dlp as described in SKILL.md Phase 1 ("下载英文 VTT 字幕")—and the provided scripts (scripts/clean_subs.py and scripts/find_timestamps_pro.py) parse that untrusted, user-generated transcript text which is then used to determine timestamps, select quotes and drive FFmpeg/Playwright rendering (generate_quotes_pro.js), so third-party subtitle/page content can materially influence tooling and actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 9, 2026, 12:14 AM
Issues
1