storm-research
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: 0.85). SKILL.md:16-17 requires “search the web” and “fetch reference pages” (public web content) and then runs simulated conversations with retrieval, so outsider-authored free text from fetched pages is ingested into the agent’s LLM context via the retrieval/WebFetch path.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata