report
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
evocommand-line utility (e.g.,evo report,evo status,evo frontier) to visualize and summarize workspace state. These commands are integral to the skill's function and are limited to read-only operations. - [COMMAND_EXECUTION]: The skill accesses local metadata and log files within the
.evo/directory to retrieve experiment details and scores for reporting purposes. - [SAFE]: The instructions explicitly prohibit the use of state-modifying or resource-intensive commands such as
evo run, Slurm task managers (sbatch,srun), and file editing, ensuring the agent remains in a read-only reporting mode.
Audit Metadata