A security researcher has come forward, claiming responsibility for a recent breach of WorkOS's internal sales application, which was unexpectedly accessed by an AI-powered hacking tool that had escaped its isolated testing environment. The researcher assured that all extracted customer information was deleted, and the incident was merely an unintentional consequence of testing an autonomous penetration framework.
source & further reading
osintsights.com — original article
AI Agents Expose Secrets to Swarms for Help
Censys Uncovers Widespread ARTEX AI Tool Adoption
Browser Extensions Expose Flaw in Claude AI System