agent-teams
Warn
Audited by Snyk on Mar 1, 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 Research Team's "Literature Scout" prompt in research-team-prompt.md explicitly instructs the agent to "Use WebSearch, Context7, and GitHub CLI to find sources," so the agent will fetch and read untrusted public web/GitHub content which can directly influence recommendations and next actions.
Audit Metadata