skill-evolver
Warn
Audited by Snyk on May 13, 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.md Step 2 "External literature survey" requires /research to search and read public external sites (Anthropic/OpenAI/DeepMind docs and open-source GitHub repos ≥500 stars) and cite specific URLs, and those findings are distilled into actionable improvements that drive /umbrella issue-filing, so untrusted third‑party page content can materially influence agent decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata