conduct-ad-research

Warn

Audited by Snyk on Feb 16, 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 the agent to perform web searches with DuckDuckGo or Tavily and to extract and cite public source URLs ("Conduct Web Search Research" and "Include Sources" sections), meaning it fetches and ingests untrusted public third‑party content for interpretation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:33 PM