brainstorm
Warn
Audited by Snyk on Jul 27, 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). The skill’s required workflow can fetch public web content at runtime via the
web-researcheragent (“search codebase + internet”), producing outsider-authored free text (web pages/community posts) that is then read and synthesized in the main context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata