@claudiolabs/claudin@1.2.3
Claudin — Claude Code opened to any LLM (OpenAI, Gemini, DeepSeek, Ollama, and 200+ models)
AI security review
scanned · by lpm-firewall-aiThe package can forward ANTHROPIC_AUTH_TOKEN in shared headers to a selected non-Anthropic provider, creating a concrete credential leak. The path requires using another provider and does not show the token going to the publisher, so this warrants a warning rather than a block.