ux-flow-auditor

Pass

Audited by Gen Agent Trust Hub on Oct 28, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a shared utility script, scripts/_skill_cli.py, which provides a run_command function. This function securely executes commands by setting shell=False and using shutil.which to resolve absolute paths, effectively preventing shell injection and path-based attacks.
  • [EXTERNAL_DOWNLOADS]: The scripts/trace_flow.py script identifies a dependency on the playwright library. It handles the absence of this library gracefully by providing standard installation instructions to the user via a terminal error message.
  • [INDIRECT_PROMPT_INJECTION]: The tool processes local .flow.json files to define interaction steps (e.g., clicks, fills) for the browser. As these files are created and maintained within the developer's local project directory under .heyeddi/, they represent a controlled data source rather than a vector for untrusted external instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 28, 2026, 09:35 PM