t-mobile
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, prompt injections, or data exfiltration attempts were detected. The skill is composed entirely of markdown documentation and instructional guidelines for a specialized role-play scenario.
- [PROMPT_INJECTION]: The system prompt defines a professional identity as a T-Mobile Strategic Advisor. It uses standard persona-building instructions and decision frameworks without attempting to bypass safety filters or override core agent guidelines.
- [DATA_EXFILTRATION]: No hardcoded credentials, sensitive local file paths, or unauthorized network operations were found. References to T-Mobile's public website and internal document paths are benign.
- [REMOTE_CODE_EXECUTION]: No scripts or external package installations are included. The skill does not perform any dynamic code execution or remote downloads.
- [OBFUSCATION]: Content is provided in plain text. No Base64, zero-width characters, or homoglyphs were detected.
- [INDIRECT_PROMPT_INJECTION]: While the skill is designed to analyze market data and customer feedback, it does not currently define specific ingestion tools or boundary markers. The threat surface is minimal as it functions primarily as a knowledge base.
Audit Metadata