refac-cli-push-down

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md examples (e.g., "Example A: PR Workflow" and "Example C: Multi-Step Data Pipeline") explicitly instruct running gh/git commands to fetch PRs, reviews, and commits from repositories—user-generated, third-party content that the agent is expected to read/interpret and use to decide next actions, enabling indirect prompt injection.