customer-service-expert
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Prompt Injection] (SAFE): No override or bypass patterns detected.
- [Data Exposure & Exfiltration] (SAFE): No sensitive data access or network activity.
- [Obfuscation] (SAFE): No encoded or hidden content.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): No external dependencies or remote script execution.
- [Indirect Prompt Injection] (INFO): The skill guidelines involve processing external data. 1. Ingestion points: Uses retrieved context and user queries (SKILL.md). 2. Boundary markers: Absent from the guidelines. 3. Capability inventory: None. The skill does not perform actions beyond text generation. 4. Sanitization: Absent.
Audit Metadata