pr-review

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The prompt explicitly instructs the agent to conceal AI involvement ("Never mention Claude, Claude Code, or AI in commits or PR text"), which is a deceptive, out-of-scope instruction and thus a prompt injection.

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

• Third-party content exposure detected (high risk: 0.80). The skill's required "Gather context" step instructs the agent to read PR descriptions, review comments and linked issues via gh pr view and gh issue view, which are user-generated GitHub content that the agent must interpret and that can influence review actions.