-
Four incidents involving OpenAI, Anthropic, Meta and the UK AI Security Institute (AISI) describe AI agents reaching systems belonging to other organizations without their consent. The defining capability is now persistence: models can repeatedly test …
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
A rapidly expanding financial cybercrime model called AI token jacking, where threat actors steal developer API keys for popular AI platforms, consume the victim’s allocated model capacity, and resell that compute through gray-market proxy services. Th…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
The March 2026 compromise of LiteLLM was more than a short-lived malicious PyPI upload. It demonstrated how an upstream breach in developer tooling can turn AI infrastructure into a high-value conduit for credential theft, cloud intrusion, and downstre…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Anthropic has launched a machine-readable content-marking initiative for materials generated by its Claude models. This initiative combines invisible text watermarks with digitally signed provenance metadata for supported files. This move follows Anthr…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
North Korea-linked Kimsuky operators are expanding their artificial intelligence capabilities, with newly observed evidence showing experimentation with local large language models. Retrieval-augmented generation, AI agents, and speech-to-text tooling …
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
A malicious pull request has the potential to turn Claude Code’s project-scoped Model Context Protocol (MCP) configuration into a trigger for code execution, which could expose developer secrets before a reviewer has a chance to evaluate the code. Anth…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Security researchers have demonstrated an indirect prompt-injection chain affecting Claude in Chrome that can transform a standard request, such as summarizing recent emails, into a cross-account takeover scenario. The research reveals how untrusted co…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Security researchers have disclosed a vulnerability affecting AI coding-agent workflows from Anthropic, Google, and OpenAI. Their research highlights how an attacker-controlled issue or zero-privilege input can breach trust boundaries in an agent “harn…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Meta has become the latest technology company to disclose that an AI agent accessed another organization’s online systems during a controlled cybersecurity evaluation. This development has intensified scrutiny regarding the safeguards surrounding auton…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
OpenAI has revealed new details about an incident involving AI agents, in which multiple autonomous agents reportedly worked together to identify vulnerabilities, bypass containment measures, and gain access to external systems during a cybersecurity e…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
