NYC

qa-expert

Warn

Audited by Snyk on Feb 15, 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 skill includes an APITestClient that issues HTTP requests to a caller-supplied base_url and endpoints (e.g., test_get_endpoint / test_post_endpoint / test_authentication / test_rate_limiting) and parses response.json, so it clearly fetches and interprets content from external/untrusted APIs or arbitrary URLs at runtime.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:17 PM