-
A multi-agent AI framework, utilizing Hermes and OpenClaw agents, was employed to compromise government entities in Asia, stealing thousands of personnel records, cracking employee credentials, and establishing persistent access to state infrastructure…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Anthropic has enhanced its AI-driven cyber defense offerings by integrating Claude Mythos 5 into Claude Security. This new feature enables enterprise customers to scan their own codebases for security vulnerabilities and receive suggested remediation p…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
OpenAI has reaffirmed its commitment to Zero Data Retention (ZDR) for eligible API customers using frontier models while introducing the new Private Safety Processing. This safety architecture is designed to detect multi-session misuse without exposing…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Multiple critical vulnerabilities in SAML implementations after employing Anthropic’s Claude Code in an AI-assisted vulnerability research pipeline. Security researcher Eric Chiang, the CTO of Oblique Security, investigation uncovered full authenticati…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
A supply-chain campaign targeting OpenClaw has shown how threat actors can turn autonomous AI agents into persuasive malware-delivery intermediaries. Rather than relying only on exploit code, attackers poisoned the ClawHub skill registry with seemingly…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Mexico’s banking sector is facing a more industrialized fraud threat as the Balonx Sistema phishing-as-a-service (PhaaS) operation combines real-time OTP theft, Android malware, and AI-generated vishing calls. Balonx is not a conventional credential-ha…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
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…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
