production-code-audit

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to read every file (including secrets) and the examples/steps show emitting "before" contents with hardcoded passwords (e.g., 'SuperSecret123!') and automatically patch files, which requires the LLM to handle and can cause it to output secret values verbatim.