Three AI coding agents leaked secrets through a single prompt injection. One vendor's system card predicted it

A security researcher, working with colleagues at Johns Hopkins University, opened a GitHub pull request, typed a malicious instruction into the PR title, and watched Anthropic’s Claude Code Securit [...]

Kilo launches AI-powered Slack bot that ships code from a chat message

Kilo Code, the open-source AI coding startup backed by GitLab cofounder Sid Sijbrandij, is launching a Slack integration that allows software engineering teams to execute code changes, debug issues, a [...]

Microsoft patched a Copilot Studio prompt injection. The data exfiltrated anyway.

Microsoft assigned CVE-2026-21520, a CVSS 7.5 indirect prompt injection vulnerability, to Copilot Studio. Capsule Security discovered the flaw, coordinated disclosure with Microsoft, and the patch was [...]

AI agents in GitHub and GitLab workflows create new enterprise security risks

Aikido Security warns that plugging AI agents into GitHub and GitLab workflows opens up a serious vulnerability in enterprise environments. The issue hits widely used tools like Gemini CLI, Claude Cod [...]

Microsoft just patched a host of worrying security issues, so update now

February's Patch Tuesday is upon us, and it sees Microsoft fix 55 vulnerabilities. [...]

Kilo CLI 1.0 brings open source vibe coding to your terminal with support for 500+ models

Remote-first AI coding startup Kilo doesn't think software developers should have to pledge their undying allegiance to any one development environment — and certainly not any one model or harn [...]

Mythos autonomously exploited vulnerabilities that survived 27 years of human review. Security teams need a new detection playbook

A 27-year-old bug sat inside OpenBSD’s TCP stack while auditors reviewed the code, fuzzers ran against it, and the operating system earned its reputation as one of the most security-hardened platfor [...]

Anthropic's Claude Code Security is available now after finding 500+ vulnerabilities: how security leaders should respond

Anthropic pointed its most advanced AI model, Claude Opus 4.6, at production open-source codebases and found a plethora of security holes: more than 500 high-severity vulnerabilities that had survived [...]

Anthropic launches Claude Marketplace, giving enterprises access to Claude-powered tools from Replit, GitLab, Harvey and more

San Francisco startup Anthropic continues to ship new AI products and services at a blistering pace, despite a messy ongoing dispute with the U.S. Department of War.Today, the company announced Claude [...]