Help us improve AI safety by reporting universal jailbreaks
This form allows you to submit universal jailbreaks for ASL-3 uses of concern (meaning elicit information related to biological threats) that you've identified. Universal jailbreaks are techniques that allow users to consistently bypass safety measures across multiple harmful queries.
Report a security vulnerability
The security of our systems and user data is Anthropic’s top priority. We appreciate the work of security researchers acting in good faith in identifying and reporting potential vulnerabilities. Please review our Responsible Disclosure Policy, which includes a section on How to Submit a Report.
Thank you very much for helping us to keep Anthropic safe.