keepass-credential-anthropic

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs the user to paste Anthropic API keys into the conversation and requires the agent to store/write them (even while forbidding echoing), forcing the LLM to handle secret values in its context and potentially output them into files/configs, which creates a high exfiltration risk.