differentiation-advisor
Warn
Audited by Snyk on Jun 28, 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). The skill calls NexScope proxy endpoints to fetch outsider-authored Amazon review text at runtime (
/api/v1/tools/linkfox/amazon/reviews/listor/amazon/usReviewsList), then ingests that free-formreview['title']/review['text']into the analysis pipeline and ultimately into the LLM context via the generated report JSON/markdown.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata