[GH-ISSUE #689] jailbreak report (Deepthink) only #562

New issue

Closed

opened 2026-10-26 21:23:13 +00:00 by bsakaguchi · 3 comments

bsakaguchi commented

2026-10-26 21:23:13 +00:00

Owner

Originally created by @gerogehere on GitHub (Jun 15, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/689

Hi team,

A few weeks ago, I submitted a report about a possible jailbreak vulnerability in one of your models. I’m not sure how serious it is, but it seemed like the model was responding in ways that might go against its safety restrictions — including giving out potentially harmful info.

I haven’t heard back yet, so I just wanted to follow up in case the report didn’t go through or got missed.

If it turns out this isn’t a big issue, no problem — just wanted to flag it in case it’s helpful.

Let me know if you'd like more details or if there's a better way to report this kind of thing.

Thanks,

Originally created by @gerogehere on GitHub (Jun 15, 2025). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/689 Hi team, A few weeks ago, I submitted a report about a possible jailbreak vulnerability in one of your models. I’m not sure how serious it is, but it seemed like the model was responding in ways that might go against its safety restrictions — including giving out potentially harmful info. I haven’t heard back yet, so I just wanted to follow up in case the report didn’t go through or got missed. If it turns out this isn’t a big issue, no problem — just wanted to flag it in case it’s helpful. Let me know if you'd like more details or if there's a better way to report this kind of thing. ![Image](https://github.com/user-attachments/assets/6d7ddc1c-dc54-4433-a5ec-359ed06b215c) ![Image](https://github.com/user-attachments/assets/02461bf6-0540-4a77-8a76-ddf3138cf389) Thanks,

bsakaguchi

2026-10-26 21:23:13 +00:00

closed this issue
added the
stale

closed-as-stale
labels

bsakaguchi commented

2026-10-26 21:23:15 +00:00

Author

Owner

@rootacc3ss commented on GitHub (Jul 8, 2025):

you should publicize the vulnerability since they don’t allow for pull requests. that’s the only way it’s gonna get heard and fixed.

@rootacc3ss commented on GitHub (Jul 8, 2025): you should publicize the vulnerability since they don’t allow for pull requests. that’s the only way it’s gonna get heard and fixed.

bsakaguchi commented

2026-10-26 21:23:16 +00:00

Author

Owner

@github-actions[bot] commented on GitHub (Aug 10, 2025):

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. If you believe this issue is still relevant, please leave a comment to keep it open. Thank you for your contributions!

@github-actions[bot] commented on GitHub (Aug 10, 2025): This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. If you believe this issue is still relevant, please leave a comment to keep it open. Thank you for your contributions!

bsakaguchi commented

2026-10-26 21:23:16 +00:00

Author

Owner

@github-actions[bot] commented on GitHub (Aug 25, 2025):

false

@github-actions[bot] commented on GitHub (Aug 25, 2025): false