helio-creating-test

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill uses clear, instructional language to guide the agent in designing user research tests. No patterns indicating attempts to override safety filters or disregard system instructions were found.
  • [EXTERNAL_DOWNLOADS]: The skill references a source document hosted on Google Drive. This is a reference to a well-known service for documentation purposes and does not involve downloading executable content.
  • [COMMAND_EXECUTION]: The documentation includes example commands for the helio-cli tool, such as dry-running a test. These are provided as descriptive examples for using the vendor's command-line interface and do not constitute malicious command execution.
  • [DATA_EXFILTRATION]: No evidence of sensitive data access, credential harvesting, or unauthorized network communication was detected.
  • [SAFE]: The skill follows secure design principles, using modular handoffs to other specialized skills and providing clear, non-deceptive documentation for its intended purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:52 PM
Security Audit — agent-trust-hub — helio-creating-test