release-skills

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly reads and interprets untrusted, user-generated content from the repository and GitHub (commit messages via git log for BREAKING CHANGE detection in Step 2 and PR author metadata via gh pr view in Step 4) to decide version bumps and to generate/attribute changelog entries, which can materially change behavior and outputs.