capstone-radar

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt explicitly instructs the agent to grep for hardcoded API keys/secrets, read file context, classify confirmed findings and include them in report entries (file:line, current approach/code), which implicitly requires extracting string literals that may be real secrets and so risks verbatim secret exfiltration.