backend-code-review

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill requires including "relevant code snippet" and file:line pointers from backend files (and flags hardcoded secrets) but does not instruct redaction, so if reviewed files contain API keys/tokens/passwords the LLM will likely output them verbatim, creating an exfiltration risk.