anthropic-docs-updater

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

• Third-party content exposure detected (high risk: 0.80). The skill automatically fetches and processes external public documentation (e.g., GitHub READMEs via raw.githubusercontent.com and GitHub API, docs.claude.com/en/release-notes, code.claude.com/docs/en/changelog, and anthropic.com/news) and integrates that content into the anthropic-expert skill, so untrusted third-party web content is read and interpreted at runtime and could enable indirect prompt injection.