team-mode

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill incorporates a local Python script, scripts/usage_by_model.py, which is intended to be run on-demand to summarize token consumption and estimated costs based on local session history.
  • [EXTERNAL_DOWNLOADS]: The documentation references the author's official GitHub repository (github.com/oil-oil/codex-team-mode) as the source for optional configuration templates (TOML files) for the different agent profiles.
  • [DATA_EXPOSURE]: The usage script reads from the local ~/.codex/sessions directory to perform accounting; however, it only extracts token count metadata and model identifiers, purposefully ignoring message content, and performs no network operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 12:30 PM
Security Audit — agent-trust-hub — team-mode