running-offsites
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Remote Code Execution] (SAFE): No executable code, scripts, or package dependencies are included in the skill files.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network operations were detected. The skill specifically instructs the agent not to request secrets.
- [Prompt Injection] (SAFE): No patterns targeting system prompt extraction or safety filter bypasses were found.
- [Obfuscation] (SAFE): All content is presented in cleartext Markdown with no encoded or hidden characters.
- [Indirect Prompt Injection] (SAFE): While the skill ingests user input to generate planning documents, it has no dangerous capabilities (such as shell access or network requests) that could be leveraged for an attack.
Audit Metadata