zai-keys

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs the agent to accept a plaintext proxy key from the human and to set/run export/installation commands that embed the agt_* token (e.g., in export ANTHROPIC_AUTH_TOKEN=agt_...), which forces the LLM to handle and potentially emit the secret verbatim into commands/output.