Docs / source reviewed

cmd-risk-plugin

Assess proposed shell commands for agent workflows

GuanWhite · Sources checked 2026-09-23

Added to this collection 2026-09-23

How this project uses Jev

Input: Shell command text and optional execution context
Jev decides: Estimate data destruction, configuration damage, exfiltration and resource-abuse risks with four Noul questions
Code executes: Code takes the maximum risk, returns a level, suggested action and CLI exit code for external hooks or MCP callers

Evidence and limitations

This is advisory; callers implement blocking and confirmation. The mock backend is keyword-based, not Jev or a security boundary. The source does not pass its model argument into the SDK request, so the reported value does not prove the model used. SDK integration and error rates were not tested here.

This project has not been run independently here. Author-reported results are not independently verified results.

Original sources

Explore related use cases

Browse this category →