web-python-sandbox-escape
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides documentation on how to perform a Python sandbox escape using the object hierarchy. It is intended for pentesting and bug hunting education, as indicated by the metadata. The code snippets provided (e.g., walking the class tree via
__subclasses__) are intended for use by a human operator in a controlled testing environment and do not constitute automated malicious behavior within the skill itself. No instances of obfuscation, remote code execution from unknown sources, or privilege escalation mechanisms targeting the agent's environment were detected.
Audit Metadata