plan-mode
Warn
Audited by Snyk on Mar 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 explicitly requires using Context7 and, if insufficient, "general web search" to verify external technical facts (see SKILL.md "Apply Research Rules" and references/research-policy.md and the README's Context7 dependency), meaning the agent will fetch and interpret public third‑party web content that can materially influence planning decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata