Skills
skills/baekenough/baekenough-skills/codex-exec/Gen Agent Trust Hub

codex-exec

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The scripts/codex-wrapper.cjs utility uses child_process.spawn with an arguments array to interface with the codex CLI. This method is resistant to shell injection as the prompt and other parameters are not interpreted by a shell environment.
  • [EXTERNAL_DOWNLOADS]: The skill documentation correctly identifies a dependency on the @openai/codex global NPM package. This is a functional requirement for a well-known service and is handled through standard user-initiated installation.
  • [DATA_EXPOSURE]: The skill includes an --output parameter that allows the AI agent to write results to a local file. This capability is transparently documented as a feature for saving generated code or analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 03:14 AM