setup-github

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

• Third-party content exposure detected (high risk: 0.90). The skill installs GitHub Actions (e.g., templates/claude-code-review.yml and claude-issue-triage.yml) that explicitly read and analyze PR diffs and issue/comments via commands like "gh pr diff", "gh pr view", and "gh issue view" (user-generated GitHub content), and then take actions (post reviews, add labels, dispatch merges), so untrusted third-party content can influence agent behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The GitHub Actions workflow uses the external action anthropics/claude-code-action@v1 (https://github.com/anthropics/claude-code-action), which is fetched and executed at workflow runtime and directly runs the supplied prompts/logic (i.e., executes remote/model code), so it is a runtime external dependency that controls agent prompts.