apiclaw
Warn
Audited by Snyk on Jun 21, 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). Outsider free text from Amazon customer reviews is ingested into the agent’s LLM context via the
reviews-rawworkflow:realtime/reviewsreturnsreviews[].body/title, which the calling skill then feeds into the per-review Map prompt (review-tag-prompt) for LLM extraction.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata