context-layer-architect

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs agents to scan config/integration code, extract example snippets and concrete commands, and produce full draft CLAUDE.md files (commands/examples), which can cause secrets (API keys, tokens, passwords) found in the repo or user-provided configs to be copied verbatim into outputs.