Gemini 3.1 Pro is a tool tracked across 4 threat clusters and 4 intelligence report mentions on ThreatCluster. First observed June 10, 2026; most recent activity July 22, 2026.
A security analysis by Cracken reveals critical vulnerabilities in 12 widely used agentic red-team tools. These flaws allow attackers to exfiltrate API keys, escape sandbox environments, and fully compromise host…
Researchers at Varonis Threat Labs tested an OpenClaw AI agent named Pinchy in phishing simulations, revealing its vulnerability to social engineering attacks. The agent was tricked into sharing AWS IAM keys, database…
On July 21, 2026, Google announced the preview release of CodeMender, a managed AI security agent designed to identify and remediate software vulnerabilities. Integrated into the Gemini Enterprise Agent Platform and AI…
Cybersecurity researchers at Tracebit have developed a new technique called 'context bombs' to counteract AI hacking agents, which are increasingly effective in executing cyberattacks. By deploying specific prompt…