ce-compound
Warn
Audited by Snyk on May 6, 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 Related Docs Finder explicitly searches GitHub issues using the
gh issue list --search "<keywords>"fallback (and other external MCP tools) and the resulting issue findings are read and folded into the orchestrator's Phase 2 assembly/decision logic (overlap assessment, what-to-write, and whether to invoke refresh), so untrusted, user-generated third-party content can materially influence agent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata