compliance-gate

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill mandates scanning for "API keys, tokens, PII" and recording findings in the compliance report (with no guidance to redact/mask or avoid echoing discovered secret values), which can force the LLM to surface secret values verbatim—creating an exfiltration risk.