arbor

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill's core functionality is implemented using a local state management script (scripts/tree.py) and standard platform tools, following isolation best practices.
  • [EXTERNAL_DOWNLOADS]: The documentation references an optional upstream CLI tool at https://github.com/RUC-NLPIR/Arbor. This is presented neutrally as an alternative for users desiring the official research implementation.
  • [COMMAND_EXECUTION]: The skill utilizes shell commands for state management and instructs the agent to perform experiments in isolated git worktrees, reducing the risk of unintended artifact modification.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 10:28 PM
Security Audit — agent-trust-hub — arbor