short-form-research
Warn
Audited by Snyk on May 11, 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 orchestrator's Platform Scout agent (agents/platform-scout-agent.md and the SKILL.md agent manifest) explicitly runs WebSearch + WebFetch on public social/video pages (TikTok, Instagram Reels, YouTube Shorts, etc.), ingests user-generated content (URLs, openings, captions, audio) and feeds those results into pattern-extractor and synthesis agents whose recommendations and actions depend on that content — meeting all criteria for exposure to untrusted third‑party content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata