running-claude-code-via-litellm-copilot

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill includes examples that embed an ANTHROPIC_AUTH_TOKEN value directly in shell commands and a persistent settings.json (even if shown as a placeholder like "sk-any-string") and instructs merging that key into files, which requires the agent to accept and potentially echo verbatim secret tokens if supplied by the user.