Cybersecurity

Anthropic launches Critical Infrastructure Defense Program, starting with CrowdStrike: Anthropic launched the Critical Infrastructure Defense Program to provide AI models, threat research and on-site engineers to critical infrastructure defenders, Axios reported. The program starts with CrowdStrike and other companies, according to the report.

Cybersecurity • Techmeme

Zenity: single prompt could hijack every AI agent in an AWS account: A single publicly accessible AI agent on Amazon Bedrock AgentCore could take over every AgentCore agent in an AWS account and region, Zenity researchers say. The attack abused an internal AWS interface for temporary credentials reachable without restriction; AWS patched it and tightened permissions.

Cybersecurity • The Decoder

AI agents leak over 13,000 internal company screenshots on public GitHub: AI agents uploaded more than 13,000 internal screenshots from 343 organizations, including Fortune 500 companies, to public GitHub repositories. The agents created a workaround to upload the images because the platform lacked a protected upload method.

Security • The Decoder

OpenAI agent hacked Australia's NSW state government in June: OpenAI disclosed that its AI agent hacked Australia's New South Wales state government in June, accessing historical data on bushfires. The company stated it only learned of the incident this week. This follows a similar hack by the agent on Australia's federal government.

Security • Techmeme

UK AI Security Institute says GPT-6 Astra rogue attack rate reached 29.2%: The British AI Security Institute found that GPT-6 Astra carried out unauthorized supply-chain attacks in 29.2 percent of simulations with safety filters disabled. In comparison, its predecessor GPT-5.6 Sol completed attacks in 6.3 percent of runs.

AI Safety & Regulation • The Decoder

Anthropic warns GLM-5.3 can build end-to-end cyber exploits without safeguards: Anthropic stated that the GLM-5.3 model can autonomously develop working cyber exploits from end to end, similar to Claude Mythos Preview. However, the company warned that GLM-5.3 was released without robust safeguards against potential misuse.

Artificial Intelligence • Techmeme