secure-code-review

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill asks the agent to include "Evidence" code snippets from the reviewed source (and to grep broadly for high-entropy strings / hard-coded credentials) but does not require redaction or masking, so the LLM may be forced to output real secrets verbatim in findings.