azure-deploy
Warn
Audited by Snyk on Feb 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill instructs the agent to fetch and interpret arbitrary deployment endpoints (e.g., "curl -s https:///health | jq .") and to "confirm endpoints are accessible", which requires reading untrusted/public HTTP responses from user-provided URLs.
Audit Metadata