cleaning-up-branches

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

• Third-party content exposure detected (high risk: 0.80). This skill fetches and displays data from remote git repositories (e.g., via git fetch --prune, git branch -r, and git log), exposing branch names and commit messages which are user-generated/untrusted content that the agent reads and presents as part of its workflow.