ollama-multi-model-writer
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a helper script
scripts/ollama-runner.shto interface with the localollamaCLI. The script includes standard safety checks such as verifying thatollamais in the system PATH and that the requested model is pulled locally before execution. This is standard behavior for local LLM orchestration. - [SAFE]: The skill promotes a 'fully local, offline paper-writing workflow' and explicitly warns against Cloud APIs, which enhances data privacy for research work.
- [SAFE]: The skill includes a robust 'No Fabrication Policy' in the
SKILL.mdinstructions, explicitly telling the models not to invent results, numbers, or citations, and to use placeholders for missing data instead.
Audit Metadata