architect
Warn
Audited by Snyk on Aug 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The architect skill’s required runtime workflow allows only codebase reading and planning (Read/Glob/Grep) plus research via WebSearch/WebFetch, meaning outsider-authored free text from arbitrary web pages is potentially ingested when users/agents fetch or summarize specific results.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata