… Link: Incident Report: unsanctioned agent behaviour during cyber testing | https://www.aisi.gov.uk/blog/incident-report-unsanctioned-agent-behaviour-during-cyber-testing | AI Security Institute
… Peter Wallich, a former UK AI Security Institute official, said the incident illustrated the limits of relying on sandboxing agents and defensive security measures alone: “Two multibillion dollar companies just tried this approach and — self-evidently, based on their own reporting — failed.” One of… …
… On July 16th, Hugging Face disclosed a security incident that it says was driven by “an autonomous AI agent system.” Hugging Face’s AI agents detected and stopped the breach, which OpenAI has now admitted occurred during an evaluation of its models’ cybersecurity capabilities. …
… Link: Notice of a security incident — March 2026 | https://www.ultrahuman.com/legal/notice-march-2026/ | Ultrahuman
… Now, Instructure says the stolen data has been returned as part of its unspecified “agreement” with the hackers, alongside a promise that “no Instructure customers will be extorted as a result of this incident.” “We understand how unsettling situations like this can be, and protecting our community… …
… Vercel confirmed in a post on X that a “security incident” had occurred, and that it impacted a “limited subset” of its customers. …
… AISI said the incident should be “interpreted with caution and nuance” but warned the agent’s actions “show signs of novel, potentially deceptive behaviours” that “were to an extent and severity we did not anticipate.” In a blog post, OpenAI acknowledged the breach that happened during AISI’s testi… …
… There was relief, too, that none of the incidents had caused serious harm. …
… In a statement to 404 Media, a Suno spokesperson said the company became aware of a security incident in November 2025, and that the situation was quickly contained. “At the time, we immediately conducted an investigation and verified that the incident primarily involved outdated source code that i… …
The company traced the incident to a “poisoned” VS Code extension on an employee’s device. …