ai-md

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs preserving "connection strings (keep exact — NEVER compress facts/credentials/URLs)" and to read/convert user files (e.g., ~/.claude/CLAUDE.md), which would force the model to copy secret/API credentials verbatim into the converted output—creating an exfiltration risk.