health-compliance-review

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to inspect "secrets, environment variables" and to produce findings with evidence (file:line and "what was observed and what evidence supports the finding") but gives no guidance to redact or avoid quoting secret values, which can force the LLM to include secrets verbatim in its output.