compose-patterns-2025

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt contains hardcoded plaintext passwords (e.g., .env.dev DB_PASSWORD=Dev!Pass123 and REDIS_PASSWORD=redis-dev-123), meaning the LLM would have secret values in-context that could be reproduced verbatim — an exfiltration risk.