Codex CLI shows a cybersecurity risk warning for benign software development prompts.

What version of Codex CLI is running?

codex-cli 0.125.0

What subscription do you have?

pro

Which model were you using?

gpt-5.5

What platform is your computer?

_No response_

What terminal emulator and version are you using (if applicable)?

_No response_

What issue are you seeing?

<img width="832" height="116" alt="Image" src="https://github.com/user-attachments/assets/99ce8c10-7c97-40c9-a313-f07f1e03b8a2" />

I believe this is a false positive safety check.

The warning shown is:
"Your conversations have multiple flags for possible cybersecurity risk. Responses may take longer because extra safety checks are on. To get authorized for security work, join the T
rusted Access for Cyber program: https://chatgpt.com/cyber"

There was no cybersecurity task, vulnerability exploitation, credential access, malware, intrusion, scanning, reverse engineering, or unauthorized system access involved.

I logged out and logged back in, but the warning still appears. Please review this as a false positive.

No matter what content is entered, this warning will pop up.

What steps can reproduce the bug?

Uploaded thread: 019dda38-c21b-71c3-91e6-6ce7716b71af

<img width="840" height="164" alt="Image" src="https://github.com/user-attachments/assets/8410b8c2-77b3-4dd8-a4a0-d27eb7b037a5" />

No matter what content is entered, this warning will pop up.

What is the expected behavior?

The expected behavior is that this warning does not pop up and the app can be used normally.

Additional information

_No response_