self-improve
Warn
Audited by Snyk on Apr 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's researcher role (si-researcher.md, "Search externally when needed: papers, benchmarks, similar projects, official docs") explicitly instructs the agent to retrieve and use external web sources as input to produce research briefs that feed planners and influence implementation, so untrusted third‑party content can materially affect decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata