research-new-brand
Warn
Audited by Snyk on Jul 10, 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). Yes—SKILL.md step 3 requires runtime
WebSearch+WebFetch, whose fetched public web page text is then used to fill thebrand-research/*.mdfiles (which become LLM-readable context for downstream State 0.1).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata