arkcli-deploy

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill's primary function is to execute the arkcli binary on the host system. It handles user-provided inputs such as endpoint names and model IDs to construct and run arkcli +deploy commands. The skill mitigates risks by instructing the agent to always use the --dry-run flag first and requiring human-in-the-loop confirmation before creating billable resources.
  • [SAFE]: The skill incorporates robust security and compliance checks, such as verifying the user's real-name identity status through arkcli auth status before attempting deployment. It also explicitly forbids the agent from using flags like --yes or environment variables to bypass interactive safety prompts in automated environments, ensuring user control over account-level changes.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 08:29 AM
Security Audit — agent-trust-hub — arkcli-deploy