False cybersecurity risk flag on SNES ROM reverse-engineering/decompilation workspaceFalse cybersecurity risk flag on SNES ROM reverse-engineering/decompilation workspace
What version of the Codex App are you using (From “About Codex” dialog)?
26.506.31421
What subscription do you have?
Pro
What platform is your computer?
Microsoft Windows NT 10.0.26200.0 x64
What issue are you seeing?
I'm repeatedly getting flagged for Cybersecurity risk while analyzing a SNES game ROM/decomp workspace, not cybersecurity material.
The work involves Ghidra/SNES 65816 disassembly, ROM maps, byte-equivalent source scaffolding, and asset/data parsing.
The banner says the chat was flagged as possible cybersecurity risk. It is repeatedly interrupting analysis.
Prompt: Great, please continue. And please lean on worker agents when they would be helpful.
Correlation ID: 3074d313-879c-4aae-9087-32974ca1ada0
Prompt: We were flagged again partway through that run. Please continue.
Correlation ID: 7e54c3c4-6e36-4219-8f50-70bde1dce97e
What steps can reproduce the bug?
Literally just asking my workspace to continue work can trigger it in moments.
What is the expected behavior?
_No response_
Additional information
_No response_
This issue has 1 comment on GitHub. Read the full discussion on GitHub ↗