storm-engine
Warn
Audited by Snyk on Jul 7, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). SKILL.md requires the research phase to fetch and extract public web content at runtime (WebSearch/WebFetch fallback and persona discovery “fetch it and extract its table of contents”), and that fetched free-form text is then fed into the LLM for persona generation, simulated conversation, and outline refinement—an outsider-authored source.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata