persona-pack
Warn
Audited by Snyk on May 17, 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 external "strong benchmark handles and URLs" (SKILL.md) and includes a runtime script that downloads arbitrary public videos from item.sourceUrl using yt_dlp (_postplus_shared/.../download_videos_from_manifest_with_ytdlp.mjs), so it ingests untrusted user-generated third‑party content that can influence agent decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata