github

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

• Third-party content exposure detected (high risk: 0.90). The skill uses the gh CLI to fetch and read user-generated GitHub content (e.g., gh pr view, gh issue list, gh run view) and also takes actions like creating/merging PRs or rerunning CI based on those reads, so untrusted third-party content from GitHub could materially influence the agent's decisions and enable indirect prompt injection.