project-guidelines-example

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes literal example secret values (e.g., NEXT_PUBLIC_SUPABASE_ANON_KEY=eyJ..., ANTHROPIC_API_KEY=sk-ant-..., SUPABASE_KEY=eyJ...) in the prompt, which are secret-like strings that could be regurgitated by the LLM and thus represent high exfiltration risk.