blog-localize
Warn
Audited by Snyk on May 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow explicitly instructs the agent to "Use WebSearch to find local case studies, brands, or scenarios" and to "Search for equivalent local statistics" (Phase 3a/3b), which requires fetching and interpreting open/public third‑party web content and using it to change outputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata