Customer Support Reply
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional, providing structured workflows and templates for customer communication. It does not include scripts, executables, or network-enabled tools.
- [PROMPT_INJECTION]: The skill's primary function is to process untrusted customer inquiries, which is an inherent surface for indirect prompt injection. However, as the skill lacks any computational capabilities or tool access, the risk is negligible.
- Ingestion points: Customer messages and inquiries (SKILL.md).
- Boundary markers: Absent; the templates use simple brackets like [issue] for data interpolation.
- Capability inventory: None detected; the skill does not utilize subprocesses, network tools, or file system writes.
- Sanitization: No sanitization or filtering of customer-provided text is instructed.
Audit Metadata