commit-security-scan
Warn
Audited by Snyk on Mar 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The references/research-requirements.md explicitly instructs using "WebFetch + arXiv fallback" and external searches ("Start with Exa MCP search"), which requires fetching and summarizing open/public web content that the agent will read and use to influence its analysis.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata