-
A newly discovered jailbreak technique named “sockpuppeting” successfully forces 11 leading artificial intelligence models, including ChatGPT, Claude, and Gemini, to bypass their safety guardrails. By exploiting a standard application progr…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
LayerX researchers have discovered how to bypass Claude Code’s safety rules using the CLAUDE.md file. This exploit allows…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
EvilTokens is a new Phishing-as-a-Service (PhaaS) platform that turns stolen Microsoft 365 tokens and AI into an end‑to‑end factory for Business Email Compromise (BEC) at scale. By combining device-code phishing, custom tooling, and large language mode…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
GrafanaGhost is a critical vulnerability in Grafana’s AI components that uses indirect prompt injection and protocol-relative URL bypasses to exfiltrate data.
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
New research from Keeper Security, reveals non-human identities and automated system-to-system interactions are becoming the top security risk for businesses in 2026.
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Hackers are abusing a fake Gemini-themed npm package to steal tokens and secrets from developers using AI coding tools like Claude, Cursor, Windsurf, PearAI, and others. The README text was copied from the unrelated chai-await-async library, a mismatch…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Cloudflare launches EmDash CMS, an AI-powered platform built to fix WordPress security flaws with sandboxed plugins, serverless scaling, and passkey auth.
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
A malicious PyPI package, hermes-px, that masquerades as a “Secure AI Inference Proxy” while secretly stealing user prompts and abusing a private university AI service. Marketed as an OpenAI-compatible, Tor-routed proxy requiring no API keys, the packa…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Anthropic’s flagship AI coding agent, Claude Code, was recently discovered to contain a critical security flaw that silently bypasses developer-configured safety rules. The vulnerability allows attackers to execute blocked commands, such as data …
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
As artificial intelligence evolves from simple chatbots to autonomous agents that actively browse the web, a new cybersecurity threat has emerged. Researchers at Google DeepMind have identified a critical vulnerability they call “AI Agent Traps.&…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
