release-management

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly uses GitHub/PR data and commit messages as inputs—e.g., SKILL.md and scripts call gh release create --generate-notes, gh release view, git log, and the smart_bump/version-manager code parse commits and generated release notes—so it ingests untrusted, user-generated content from GitHub which the agent reads and uses to decide version bumps and release actions.