code-duplication-detector

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to extract and include verbatim code blocks and command outputs in reports (e.g., code excerpts, lines, and shells reads), so any hard-coded API keys or secrets present in the scanned files would be reproduced in the LLM output, creating an exfiltration risk.