case-study-writing
Warn
Audited by Snyk on Jul 7, 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). SKILL.md instructs running
belt app run tavily/search-assistantandexa/search/answerwith user-supplied queries, which at runtime fetches public web content and feeds the retrieved text into the agent/LLM context (indirect prompt-injection risk from outsider-authored web pages).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata