implementing-semgrep-for-custom-sast-rules

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The scripts/agent.py clearly fetches JSON from a user-supplied target URL (requests.get to {target}/api/v1/status and {target}/api/v1/compliance), ingests and interprets that untrusted third‑party content to generate findings and a risk_level that affect actions and reporting.