api-research
Warn
Audited by Snyk on Mar 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly requires web_search and direct testing via curl of public API endpoints (Step 1 and Step 2 and the listed public API URLs), so the agent will fetch and interpret untrusted third-party web/API content as part of its workflow.
Audit Metadata