Developer Fernando Irarrázaval's AI agent experiment drew over 6,000 hack attempts from more than 2,000 attackers. No one ...

Ongoing research into AI agent framework security identified an exploit chain in AutoGen Studio (AutoGen’s open-source prototyping user interface) that allows untrusted web content rendered by a ...

ESET Research analyzes Gamaredon’s new toolset and the group’s growing reliance on legitimate online services to hide its C&C ...

The more recent Home Assistant updates are closing information leaks, among other things. There is also a new version of Home ...

Cross-Repo Code Review, Custom Rules Miner, and Skill Review Standards give enterprises the governance infrastructure to ...

OrcaRouter, the OpenAI-compatible LLM gateway, today published The AI Threat Report 2026 and made two of its security controls available at no cost to all users: the agent Firewall and input/output ...

The Meta-Harness Omnigent combines AI agents like Claude Code and Codex under a common policy and collaboration layer – under ...

With the proper setup and guidance, you can have Claude Code, Codex, Posit Assistant, and other coding agents writing R code ...

Cisco patched CVE-2026-20262 in Catalyst SD-WAN Manager after limited exploitation, with federal fixes due June 29.

Google Open Knowledge Format (OKF) v0.1 gives AI agent teams a vendor-neutral Markdown spec for sharing organizational ...

Actively exploited CVE-2026-5027 lets attackers write files to arbitrary locations on vulnerable Langflow servers, creating a path to remote code execution and full system compromise.

Once a signal of exploitation risk, Willison’s ‘lethal trifecta’ describes the baseline operations of every AI agent today.