git-automation

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly reads and interprets untrusted, user-generated repository content (e.g., commit messages via git log/analyze_commit_impact, changelog generation/generate_changelog, and GitHub-derived notes via gh release create --generate-notes) pulled from remote repositories/GitHub, exposing the agent to indirect prompt injection risks.