Repository navigation
Invalid prompt: your prompt was flagged as potentially violating our usage policy. for GPT6 #49440
Description
Activity
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
- BUG：GPT-6 Astra flags every harmless prompt as a policy violation in Codex Desktop and Work #48713
- [Bug] All GPT-6 models available to my account are unusable due to invalid_prompt #49213
- Invalid prompt Response #49120
- GPT-6 Sol/Luna/Astra falsely reject benign prompts with Invalid prompt safety error #48817
- Harmless prompts consistently rejected as "Invalid prompt" due to potential usage policy violation #48865
Powered by Codex Action
What version of the Codex App are you using (From “About Codex” dialog)?
26.924.22138
What subscription do you have?
Bussiness premium
What platform is your computer?
Darwin 27.0.0 arm64 arm
What issue are you seeing?
"Invalid prompt: your prompt was flagged as potentially violating our usage policy."
Steps to reproduce:
Expected behavior:
Astra should return a normal response to a simple prompt.
Actual behavior:
The request is rejected as potentially violating the usage policy.
I have attached a screenshot of the error.
Could you please help check whether Astra is adding any system prompt/context that may be triggering the policy filter?
What steps can reproduce the bug?
Feedback ID: 01a0effc-0bac-75c2-a5de-59a0b81a63b2
What is the expected behavior?
reply me with hello
Additional information
No response