commit-message-creation

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md Process (Step 1) and the "Prefer remote tools" / "External Content Handling" sections explicitly direct the agent to use MCP/GitHub/GitLab tools to search and read issues, PRs, discussions and external URLs (user-generated public content) and to incorporate that context when generating commit messages, which clearly exposes the agent to untrusted third-party content that could influence actions.