sandbox-status

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill serves as a status reporter, inspecting the execution environment to confirm sandbox status and active security policies.
  • [EXTERNAL_DOWNLOADS]: The instructions and examples refer to the '@anthropic-ai/sandbox-runtime' package and official Anthropic repositories for documentation. These are established resources within the tool's ecosystem.
  • [COMMAND_EXECUTION]: Employs standard system utilities such as 'jq' and 'which' to audit platform-specific isolation features like bubblewrap and Seatbelt.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 07:36 AM
Security Audit — agent-trust-hub — sandbox-status