english
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified. The skill is entirely instruction-based (prompt-only) and focuses on text transformation for language coaching.
- [SAFE]: Tool access is appropriately restricted to 'AskUserQuestion' in the YAML frontmatter, preventing the agent from performing unintended actions or accessing the file system/network.
- [SAFE]: The installation instructions point to the official repository of the verified author (tw93/Waza), following standard platform practices.
- [SAFE]: The skill processes user-provided text for coaching purposes but lacks the capabilities (like file writing or command execution) to be exploited via indirect prompt injection.
Audit Metadata