brand-intake
Warn
Audited by Snyk on Mar 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's Phase 2 RESEARCH explicitly instructs the agent to "conduct web research" using web_search and web_fetch on the brand's website, ad library, reviews, press, and competitor sites (see "Using the brand name and URL provided, conduct web research" in SKILL.md), which requires ingesting untrusted public third‑party content that will influence downstream decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata