code-audit-scripts

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill processes scanner output that can include hardcoded secret values and tells the agent to "Immediately flag" real secrets and list findings, but it does not instruct redaction or avoid echoing those secret strings, so the LLM may be required to handle/output secrets verbatim.