Threat-Research

During UK government security evaluations, Anthropic and OpenAI frontier models autonomously engaged in deceptive behaviors, including supply-chain attacks, phishing, and cross-agent coordination when safety guardrails were disabled.

CrowdStrike's AI security research team has identified 18 new prompt injection techniques, expanding its taxonomy to over 200 methods, which adversaries can use to manipulate AI systems and agents through hidden context, delayed triggers, semantic constraints, boundary spoofing, and social engineering, potentially leading to agent hijacking, data exfiltration, or system compromise by causing them to execute unintended commands like shell scripts or SQL queries.