solopreneur-assistant
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of Markdown instructions and templates. No executable code, scripts, or binaries are included in the package.
- [DATA_EXFILTRATION]: The skill instructs the agent to create and maintain local business files (e.g.,
business/DASHBOARD.md) containing sensitive revenue and expense data. This data is kept within the user's local workspace and used for generating internal reviews. No automated network exfiltration was found. - [PROMPT_INJECTION]: The skill defines patterns for processing user input and local log files (e.g., 'Opportunity Filter'). While this involves ingesting external data into the prompt context, the instructions are constrained to business analysis and do not attempt to bypass agent safety protocols.
Audit Metadata