detecting-broken-object-property-level-authorization

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

• Third-party content exposure detected (high risk: 1.00). This skill's runtime code (scripts/agent.py and the BOPLAScanner in SKILL.md) issues HTTP requests to arbitrary base_url/endpoints provided at runtime and parses the returned JSON to decide tests and follow-up actions (e.g., which fields to inject and whether to restore), so it directly ingests untrusted third‑party API content that can materially influence tool behavior.