overnight-agent-guard
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill scripts use the shell
evalcommand to execute developer-provided commands for agent tasks and verification checks. - Evidence:
bin/night-preflight(line 92),bin/verify-gate(line 38), and thetemplates/night-run.shscaffold (line 51) utilizeevalto run commands passed as arguments or environment variables. - Context: This is the primary intended functionality of the skill, acting as a wrapper to automate and safely bound the execution of other developer tools and agent processes.
Audit Metadata