security-scan

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs the agent to load the entire codebase (including any hardcoded secrets) and runs unredacted secret-grepping and scanning steps without instructing redaction, which means the LLM will likely ingest and may output secret values verbatim in findings—high exfiltration risk.