claude-code-hooks

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

• Third-party content exposure detected (high risk: 0.70). This skill documents and supports HTTP hooks (and prompt/agent hooks) that send JSON to arbitrary URLs and parse response bodies as decisions—see references/input-output.md and references/hook-lifecycle.md—so responses from external endpoints could be untrusted third-party content that materially affects tool use (e.g., permission decisions).