False cybersecurity-risk block in Codex 5.5 Extra High for personal job-application workflow

What version of the Codex App are you using (From “About Codex” dialog)?

26.429.61741

What subscription do you have?

Plus

What platform is your computer?

Microsoft Windows NT 10.0.26200.0 x64

What issue are you seeing?

The Codex Agent (5.5 Extra High) is blocked by the model to finish its workflow coded in the skill file. The workflow is for shortlisting job offers from 2 jobs sites and applying for those jobs. All by browsing the UI like a human would do. Some days it went through when prompted to continue after it'd stopped but in other days it didn't.
I think the risk I am taking with this is very small as I run it on my personal laptop with no credentials shared in any environments. I don't have any very valuable info, either. So, I am ready to take whatever risk the model is flagging but I am just not allowed to do so. I don't want to use older models as they are not so intelligent and the filtering does not provide the expected outcomes.

What steps can reproduce the bug?

You should have my skill (workflow) in order to be able to reproduce it. I will not share it here, Uploaded thread: 019dfba6-212b-7bf2-8126-fe295a973aa6

What is the expected behavior?

The expected behavior is the Agent to finish the work end-to-end in the way described in the custom skill I created.

Additional information

_No response_