External Model or Provider Selection
- Category
- Excessive Agency
- Confidence
- 90% confidence
- Finding
The skill explicitly instructs users to run Claude Code prompts against an alternate external provider with no gating or consent checkpoint. In a coding-agent context, this can redirect sensitive prompts, code, and derived outputs to a third party, which raises meaningful confidentiality and compliance risk.
- Content
export ANTHROPIC_API_KEY="sk-kimi-..."
claude # Interactive / 交互模式 claude --print "Your prompt" # One-shot / 单次执行
text Claude Code auto-appends `/v1/messages`. No other changes.
