[Bug]: Codex Security Plugin not recognised in T3 Code
Nobody has claimed this yet.
- Dominant language
- TypeScript
- Stars
- 23k
- Forks
- 5.9k
- Avg merge
- 11h 14m
- Merged PRs (30d)
- 357
Description
Before submitting
- I searched existing issues and did not find a duplicate.
- I included enough detail to reproduce or investigate the problem.
Area
Not sure
Steps to reproduce
- In ChatGPT macOS app install Codex Security plugin https://learn.chatgpt.com/docs/security/plugin
- Enroll in OpenAI Trusted Access For Cyber (TAC) program https://ai.georgeliu.com/p/chatgpt-codex-flagged-my-security
- Setup OpenAI Advanced Account Security https://ai.georgeliu.com/p/openai-trusted-access-for-cybers
- Then open T3 Code app and select Codex GPT-5.6 Sol and try to do a security audit of your code
Expected behavior
When you do a security audit from ChatGPT macOS app using GPT-5.6 Sol, it will trigger a TAC security request access and grant TAC level 1 access
I expect the same from T3 Code session with Codex GPT-5.6 Sol
Actual behavior
However with T3 Code, GPT-5.6 Sol says it is unable to see the Codex Security Plugin so blocks any security work through TAC defensive security program when done in T3 Code. While it works in ChatGPT macOS app with Codex v0.152.0
GPT-5.6 Sol returns
TAC access returned unknown with no grant levels, so protected scan output access may not be available.
Impact
Blocks work completely
Version or commit
t3 code 0.0.37 (cefec32d6fc5)
Environment
macOS 15.7.9, Codex v0.152.0
Logs or stack traces
Screenshots, recordings, or supporting files
No response
Workaround
No response
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the issue in T3 Code 0.0.37 on macOS 15.7.9 with Codex v0.152.0, then compare the plugin and TAC behavior with the ChatGPT macOS app, where it works. Trace the T3 Code session's Codex integration and confirm done when the Codex Security Plugin is recognised and the expected TAC access is returned.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- ai, desktop
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100