token-saver-codex
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run a bundled Node.js script to perform a configuration audit. This is a legitimate diagnostic function of the skill.
- Evidence:
SKILL.mdcontains the instruction:node <this skill's directory>/scripts/audit.mjs --agent codex. - [SAFE]: The bundled script
scripts/audit.mjsperforms read-only analysis of local agent configuration files (such asconfig.toml,CLAUDE.md, and.cursorrules). A manual review confirms the script contains no network exfiltration logic, no file-write operations, and no obfuscation. Its behavior is entirely consistent with the skill's stated purpose of token optimization.
Audit Metadata