coding-router

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

• Third-party content exposure detected (high risk: 0.80). The skill's required review/workflow steps (e.g., skills/coding-agent/SKILL.md, references/WORKFLOW.md and references/reviews.md) explicitly instruct running GitHub CLI commands like gh pr view, gh pr diff, and gh pr list to fetch and review PR metadata and diffs (user-generated public content), which the agent is expected to read and act on as part of its workflow—exposing it to untrusted third-party content that could carry indirect prompt-injection instructions.