arch-review
Warn
Audited by Snyk on May 15, 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 Step 0 (Scope & Feasibility Challenge) explicitly instructs the agent to "Search the literature" and run web searches (and the DESIGN.md allowed-tools includes WebSearch), so the agent will ingest open/public web content (potentially user-generated) and use those findings to influence its review and decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata