venice-chat
Warn
Audited by Snyk on Aug 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: 0.30). SKILL.md describes Venice’s
/api/v1/chat/completionsrequest where outsider-providedmessagescontent can trigger Venice server-side web search/scraping (e.g.,venice_parameters.enable_web_search,enable_web_scraping,include_search_results_in_stream), meaning the LLM workflow may ingest free text indirectly sourced from non-first-party pages chosen based on user input.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata