managing-git-workflow

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and read PR metadata, diffs, and comments from GitHub (e.g., "gh pr view <PR_NUMBER> --comments", "gh pr diff <PR_NUMBER>", "gh api .../pulls/<PR_NUMBER>/comments") and to load Linear issues ("mcp__linear__get_issue" or Linear web UI), which are untrusted user-generated third-party contents that the agent is expected to interpret and use to drive review decisions.