sandbox-python-executor
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to enable host-native Python execution for tasks such as manifest parsing, skill scaffolding, and package inspection. It includes rules to keep repository access read-only and avoid exposing credentials during execution.- [PROMPT_INJECTION]: The skill identifies a potential attack surface by allowing the execution of untrusted scripts. It addresses this risk by mandating that the agent inspect target scripts before running them and by discouraging the simulation of results without actual execution.
Audit Metadata