hooks-configuration

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

• Third-party content exposure detected (high risk: 0.90). The skill's HTTP hook type and "HTTP Hook Configuration" (e.g., url: "https://hooks.example.com/pre-tool-use") explicitly send hook data to arbitrary HTTPS endpoints and ingest their JSON responses, which are then used to make permission decisions and modify inputs, allowing untrusted third-party content to influence agent behavior.