damage-numbers
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): No behavioral overrides or instructions targeting the AI's core logic were found.
- [Data Exposure & Exfiltration] (SAFE): The skill does not access sensitive local files or perform network requests to untrusted domains.
- [Remote Code Execution] (SAFE): There are no patterns involving the download and execution of remote scripts or binary files.
- [Indirect Prompt Injection] (SAFE): Although the UI renders variable data (damage values), there are no high-privilege tools or capabilities available for exploitation.
- [Persistence] (SAFE): No mechanisms for establishing persistence on the host system are present.
Audit Metadata