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
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 11, 2026, 03:38 PM
Issues
1