thinking-partner
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains no executable code or scripts, reducing the risk of technical attacks such as command execution or privilege escalation.
- [PROMPT_INJECTION]: The instructions focus purely on defining a conversational persona (a 'thinking partner') and do not attempt to bypass safety guidelines, override system instructions, or extract system prompts.
- [DATA_EXFILTRATION]: No network operations, API calls, or patterns indicating data exfiltration were found. While the skill mentions searching a 'vault' (standard for note-taking environments), it does not suggest sending this data to external servers.
- [REMOTE_CODE_EXECUTION]: There are no patterns of downloading or executing remote code. All logic is contained within the natural language instructions.
Audit Metadata