llm-workspace-management
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a well-structured tool for managing local knowledge bases. It performs standard file operations within user-defined directories to maintain indexes, statistics, and reports.
- [PROMPT_INJECTION]: The skill processes user-provided wiki content to generate summaries and cross-wiki comparisons. While this represents an indirect prompt injection surface, the skill is restricted to local operations and lacks network capabilities, significantly mitigating the risk.
- [DATA_EXFILTRATION]: No network activity or external data transmission was detected. The skill specifically defines boundaries that exclude access to sensitive configuration files containing API credentials.
Audit Metadata