reviewing-english-prompts
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a technical English coaching feature that operates alongside task execution. It includes explicit privacy constraints, such as prohibiting the transmission of user prompts to external services for language evaluation.
- [SAFE]: No evidence of prompt injection, data exfiltration, or unauthorized command execution was found. The instructions prioritize preserving the user's original request and constraints.
- [SAFE]: The skill uses clear, well-documented markdown files for terminology guidance and evaluation cases without any obfuscated content or external dependencies.
Audit Metadata