reputation-respond
Warn
Audited by Snyk on Jul 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). SKILL.md Phase 1 instructs the runtime workflow to use WebSearch and WebFetch to collect “Full review text” from third-party review platforms (outsider-authored free text), which then becomes part of the LLM’s context for Phase 3 response generation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata