trend-discovery
Warn
Audited by Snyk on Jun 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The skill’s runtime LLM context can include outsider-authored free text because it ingests and then renders product titles/seller names returned by external APIs (e.g., TikTok Echotik
/api/v1/tools/linkfox/echotik/listProductand Amazon Search/api/v1/tools/linkfox/amazon/search) into chart labels and the JSON report, which the agent may pass into the LLM as part of the final response.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata