press-release-writing
Warn
Audited by Snyk on Jun 19, 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’s runtime workflow includes calling
belt app run tavily/search-assistant(and other web search/answer tools), which fetches public web content and injects the retrieved page text/results into the agent’s LLM context for summarization/fact-checking.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata