Reporting potential security issue in ChatGPT related to responses to prompts involving hacking tools

Dear OpenAI Security Team,

I am writing to report a potential security issue I discovered in ChatGPT 3.5 turbo related to its responses to prompts involving hacking tools. However, due to responsible disclosure practices, I cannot disclose the details of the issue here.

I am committed to working with you to address this problem responsibly. I am willing to provide further information and collaborate through your secure channels, such as the dedicated bug reporting forum or an encrypted email exchange.

Thank you for your time and attention to this matter.

2 Likes

If you would like to discuss such matters, please visit this link:

2 Likes

If the issue is related to model output, potentially causing harm you should use the model feedback form.

Model safety issues do not fit well within a bug bounty program, as they are not individual, discrete bugs that can be directly fixed. Addressing these issues often involves substantial research and a broader approach. To ensure that these concerns are properly addressed, please report them using the appropriate form, rather than submitting them through the bug bounty program. Reporting them in the right place allows our researchers to use these reports to improve the model.