branch-cleaner

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

• Third-party content exposure detected (high risk: 0.80). The skill fetches and inspects remote repository data (git fetch --prune, git branch -r, git for-each-ref) and optionally reads GitHub PRs via gh pr list/gh pr view, which consumes untrusted user-generated content from remote repositories/public GitHub that the agent would read and interpret.