git

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflows explicitly fetch and inspect remote, user-generated repository data (e.g., "git fetch origin", "git pull", "git remote add upstream https://github.com/original/repo.git", "gh pr view", and commands that run git diff/git log against origin/main) so the agent will ingest and interpret public repo commits, diffs, and PR descriptions from third-party sources which can materially influence subsequent git actions.