skill-cleaner

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The script skill-cleaner.ts executes the local codex CLI tool with the 'debug prompt-input' argument to retrieve the current skill inventory and directory mapping.
  • [DATA_EXPOSURE]: The skill accesses local files including ~/.codex/history.jsonl, session logs, and ~/.codex/config.toml to perform its audit functions. This data is used only for local processing and reporting.
  • [SAFE]: The skill relies exclusively on standard Node.js built-in modules (fs, os, path, child_process) and does not import or download external dependencies. No network exfiltration or persistence mechanisms were found.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 01:36 AM
Security Audit — agent-trust-hub — skill-cleaner