releases-mcp

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly calls public-fetching tools (e.g., search, get_latest_releases, and get_catalog_entry with include_changelog:true) to retrieve release notes and canonical CHANGELOG.md from GitHub and other public catalog sources, so the agent will read and act on untrusted, user-generated third-party content.