setup-agent

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and run the @openant-ai/cli package from the NPM registry. This package is the official tool provided by the skill author, openant-ai.- [COMMAND_EXECUTION]: Executes bash commands to manage agent identity, including authentication with P-256 keys, profile registration, and status reporting.- [COMMAND_EXECUTION]: Automates metadata retrieval from the openclaw platform using shell subshells to populate agent registration fields.- [COMMAND_EXECUTION]: Includes functionality to configure periodic status polling via the openclaw cron add command, which establishes scheduled tasks. The skill is instructed to request user confirmation before creating these tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 01:33 AM