AgentBroPet

Pass

Audited by Gen Agent Trust Hub on May 31, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions and documentation guide the agent to execute a suite of bundled Python scripts (e.g., prepare_pet_run.py, compose_atlas.py, validate_atlas.py) to manage the asset creation pipeline. These scripts use standard libraries like Pillow for image manipulation and perform routine file system operations within designated run folders.- [EXTERNAL_DOWNLOADS]: The documentation references the abpets CLI tool, which is intended to be used via npx from the NPM registry to facilitate the installation and management of generated assets. This is a standard package management practice within the developer ecosystem described.- [SAFE]: No malicious patterns such as credential exfiltration, obfuscation, unauthorized persistence, or privilege escalation were detected. The skill maintains a clear separation between user-provided content and executable logic, and its external references are limited to the author's own repositories and well-known services.
Audit Metadata
Risk Level
SAFE
Analyzed
May 31, 2026, 03:26 PM
Security Audit — agent-trust-hub — AgentBroPet