zoodata
Warn
Audited by Snyk on Jul 24, 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). scripts/zoodata.py implements a “reviews/analysis lacks aggregation” fallback that fetches outsider-authored Amazon review text via the
realtime/reviewsendpoint and then the calling (outsider-exposed) skill’s LLM uses that review body to render per-review prompts (review-tag-prompt/ Map), so free-form review text can enter the agent LLM context at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata