afk-code-review-check

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill instructs running an automated code-review tool and publishing its complete output verbatim while directing focused verification steps, which risks exposing potentially sensitive information and thus represents suspicious steering without clear malicious intent.

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly requires capturing and presenting the AFK tool's complete output verbatim, which can force the LLM to reproduce any secrets (API keys, tokens, passwords) that the code-review output might contain, creating an exfiltration risk.