review
Warn
Audited by Snyk on Apr 25, 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 AUTOPLAN Phase 0 "Landscape Check" explicitly instructs the agent to perform WebSearch and "feed" those external search results into the Premise Challenge and Dream State Mapping (SKILL.md, "Landscape Check" / Phase 0), so it fetches and interprets public web content that can materially influence decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata