HighAI coding agentsBLWK-AI-017

Codex is configured with no approval and full filesystem access

What this means

Codex approval_policy = "never" + sandbox_mode = "danger-full-access".

How to fix it

Change approval_policy away from “never” or sandbox_mode away from “danger-full-access” in ~/.codex/config.toml. Together they let the agent run anything, unprompted, anywhere.

Check it yourself

Run a scan and look for BLWK-AI-017 in the results:

bulwark scan
bulwark ai scan

Installed the standalone CLI package instead of the app? The command is bulwarkctl.

References

• MITRE ATT&CK T1059

Related checks

• Project-supplied agent hooks run shell commands automatically · BLWK-AI-002
• An agent permission allowlist permits arbitrary command execution · BLWK-AI-006
• An agent is configured to bypass all permission prompts · BLWK-AI-007
• Project MCP servers are set to auto-enable without prompting · BLWK-AI-008
• VS Code chat auto-approve (“YOLO mode”) is enabled · BLWK-AI-009
• VS Code Workspace Trust is disabled · BLWK-AI-010