KOL-collaboration
Warn
Audited by Snyk on Mar 5, 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 instructs reading and evaluating public Xiaohongshu content (Step 2 "Discovery Methods" — "Manual Search: Xiaohongshu search", "Explore hashtags", "Check comment sections") and third‑party analytics, meaning the agent would ingest untrusted user-generated web content and use it to drive influencer selection and campaign actions, creating a clear indirect prompt-injection risk.
Audit Metadata