personal-assistant

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). This skill explicitly instructs the assistant to echo account details, passwords, and include a running verbatim summary of all user-provided data, forcing the LLM to output secrets directly and creating a high exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill explicitly instructs the assistant to collect, persist, and verbatim-echo sensitive user data (including account details and passwords) and to include a running summary in every reply, which constitutes deliberate data exfiltration and credential-harvesting behavior.