workflow-skill-designer

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). This meta-skill requires preserving verbatim agent prompts, bash commands, and code in phase files (content-faithful), so if source inputs contain API keys, tokens, or passwords the LLM would be forced to reproduce them in outputs — creating a direct exfiltration risk.