template-renderer

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt explicitly says it "integrates Public, Confidential (Company/Client), and Personal knowledge tiers, prioritizing the most specific secrets" for rendering templates, which implies the agent may need to substitute secret values verbatim into rendered output (exfiltration risk) unless stronger safeguards are specified.