pi-web-search
Warn
Audited by Snyk on Jul 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). SKILL.md describes runtime use of the
web_search/Exa → Perplexity → Gemini pipeline (public web content fetched at runtime, i.e., outsider-authored text), which is then ingested as “synthesized answers with citations” into the agent’s LLM context; theworkflow:"none"setting only suppresses a popup, not the web content itself.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata