amazon-analysis
Warn
Audited by Snyk on Aug 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In scripts/zoodata.py, the “review fallback toolkit” path fetches raw reviews via the reviews-raw/realtime reviews API, renders prompts including each review’s free text (review.get("title")/review.get("body")), and feeds that free text into the caller’s LLM for tagging/reducing/aggregation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata