persona-pack
Warn
Audited by Snyk on May 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly requires deriving personas from benchmark artifacts and "strong benchmark handles and URLs" (SKILL.md) and includes a runtime script download_videos_from_manifest_with_ytdlp.mjs that fetches videos from item.sourceUrl (public URLs via yt_dlp), so it ingests untrusted, user-generated third-party content that can influence persona decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata