openui

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill prompt contains example shell commands that embed API keys verbatim (e.g., echo "OPENAI_API_KEY=sk-your-key-here" > .env and OPENAI_API_KEY=sk-test pnpm run build), which encourages the LLM to output secret-like values directly and thus creates an exfiltration risk.