github-code-search

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly directs queries to grep.app (e.g., curl or fetch to https://grep.app/api/search and via the grep MCP server) to retrieve and process code from public GitHub repositories, which are untrusted, user‑generated third‑party content that the agent will read and act on.