Skills
Navigate
skills/cskwork/agent-skills/gpt-image-2/Gen Agent Trust Hub

gpt-image-2

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the codex CLI and python3 to interact with OpenAI's infrastructure and process session files.
  • The scripts/gen.sh script invokes codex exec with the --enable image_generation flag to trigger image creation.
  • It performs a snapshot of the ~/.codex/sessions directory to identify new rollout files, which it then processes using a Python script.
  • The scripts/extract_image.py script includes safety checks to prevent writing the resulting image to sensitive system directories (e.g., /etc, /bin, /var/root).
  • The logic is scoped to reading session files generated during the specific invocation, minimizing access to unrelated local data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 10:36 AM