changelog-review

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow explicitly directs fetching and parsing the public changelog at https://raw.githubusercontent.com/anthropics/claude-code/main/CHANGELOG.md and using its contents to decide actions (generate reports, create issues, update plugins), so third-party content can directly influence agent behavior.