code-examples

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

• Third-party content exposure detected (high risk: 1.00). The skill calls the public grep.app search API (e.g., https://grep.app/api/search?q={query}) to retrieve code snippets from millions of public GitHub repositories, so the agent ingests untrusted, user-generated third-party content to read and interpret.