effect-monitoring

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: 0.80). The skill's required monitoring workflow instructs the agent to read and act on user-generated content and external analytics (see "Comment Sentiment Tracking" in Step 4 and the "Third-Party Tools: Huitun Data, Chanmama, Xinhong Data" / "Platform Analytics" entries in Implementation), which requires ingesting public, untrusted third‑party content that can materially influence decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 11:41 AM