zg-customer-case-collector
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a structured interviewing agent. It specifically instructs the AI to avoid编造 (fabricating) data and to maintain customer anonymity by default.
- [DATA_EXPOSURE_EXFILTRATION]: The instructions explicitly forbid the collection of sensitive personal information such as phone numbers, IDs, or contract details. It also includes a safety check regarding file exports, stating that data should not be sent externally by default.
- [INDIRECT_PROMPT_INJECTION]: While the skill ingests untrusted user input during the interview process, it lacks dangerous capabilities (like arbitrary code execution or network requests). It includes clear instructions to distinguish between facts, user quotes, and inferences, which serves as a prompt boundary practice.
- [COMMAND_EXECUTION]: No shell commands, dynamic context injection, or privilege escalation patterns were found in the provided files.
Audit Metadata