arch-performance-optimization

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt mandates citing file:line and grep results as evidence for every claim and to search the codebase for patterns before acting, which can require the agent to paste verbatim file contents (including any API keys, tokens, or passwords found), creating an exfiltration risk.