customer-support
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and does not include any executable scripts, shell commands, or binary files.
- [SAFE]: No external network operations, remote code downloads, or third-party package dependencies were detected.
- [SAFE]: The instructions provide a standard professional persona for customer support without any attempts at prompt injection, safety bypass, or credential harvesting.
- [INDIRECT_PROMPT_INJECTION]: As a customer support skill, it is designed to process untrusted customer input (e.g., chat messages, support tickets). While this presents a theoretical surface for indirect prompt injection, the skill itself does not provide any logic that would escalate privileges or execute code based on that input.
Audit Metadata