pm-advisory-board
Warn
Audited by Snyk on Jul 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). SKILL.md:39-40 describes a required runtime step “WebSearch” to unify external facts, which typically fetches public web pages and injects their readable text into the agent’s LLM context (outsider-authored free text via runtime web content).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata