motivation
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious code, obfuscation, or unauthorized network operations were detected. The skill operates by providing behavioral templates and referencing local markdown files for personalization.
- [NO_CODE]: The skill is composed entirely of Markdown documentation and prompt instructions. There are no associated scripts (Python, Node.js, etc.) that perform logic, reducing the technical attack surface.
- [PROMPT_INJECTION]: The skill utilizes a 'Wins Bank' stored in
~/.openanalyst/motivation/wins-bank.mdwhich includes 'User's Own Words'. While this represents an indirect prompt injection surface (ingesting external data into the prompt context), the risk is negligible as the skill lacks high-privilege capabilities such as shell execution or network exfiltration. - [DATA_EXFILTRATION]: Data access is localized to the
~/.openanalyst/directory. No evidence of credentials, API keys, or mechanisms to transmit this data to external servers was found.
Audit Metadata