runhuman-testing

Pass

Audited by Gen Agent Trust Hub on May 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and fetches resources from the vendor's official domain and repositories.
  • Fetches the GitHub Actions setup guide from runhuman.com.
  • References the official GitHub Action at volter-ai/runhuman-action.
  • Instructs the installation of the runhuman CLI via npm.
  • [COMMAND_EXECUTION]: The skill relies on the execution of the runhuman CLI tool to perform its primary functions.
  • Includes commands for authentication (runhuman login), project management (runhuman projects), and testing workflows (runhuman job create).
  • Provides structured patterns for asynchronous job management and result retrieval.
  • [SAFE]: All identified behaviors are consistent with the skill's purpose as a service integration tool. The use of vendor-owned infrastructure and standard CLI patterns does not present an elevated security risk within the scope of its intended use.
Audit Metadata
Risk Level
SAFE
Analyzed
May 30, 2026, 05:12 PM
Security Audit — agent-trust-hub — runhuman-testing