twitter-thread-creation
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: 0.75). SKILL.md describes runtime steps that call external research tools (e.g.,
belt app run tavily/search-assistantandinfsh/agent-browserwith a URL), which can fetch and ingest outsider-authored web page text into the agent/LLM context for generation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata