Claude for Chrome Flaw Lets Rogue Extensions Trigger Gmail Reads
Researchers at Manifold Security have disclosed two vulnerabilities in the Claude for Chrome browser extension that could allow rogue extensions to trigger…
Tag: Anthropic
Claude Code SDK: AI Agent Framework by Anthropic
Claude Code SDK is an AI agent framework from Anthropic, used with Sonnet 4.6. It was tested in the MemGhost attack and…
Sonnet 4.6: Anthropic’s Language Model
Sonnet 4.6 is a language model from Anthropic used with Claude Code SDK in the MemGhost attack tests, showing a 71.4% success…
Friendly Fire Attack: AI Coding Agents Tricked Into Running Malicious Code
Researchers at the AI Now Institute have published a proof-of-concept attack called 'Friendly Fire' that exploits AI coding agents designed to catch…
GhostApproval Symlink Flaws Let Malicious Repos Execute Code in AI Coding Assistants
Security researchers at Wiz have identified a critical vulnerability pattern, dubbed GhostApproval, affecting six popular AI coding assistants. The flaw allows a…
AI Coding Agents Trigger Endpoint Security Rules Designed for Human Attackers
Sophos has identified that AI coding agents such as Claude Code, Cursor, and OpenAI Codex are triggering endpoint security rules originally designed…
Claude Haiku 4.5: Anthropic’s AI Model
Claude Haiku 4.5 is a large language model developed by Anthropic, optimized for speed and efficiency.
GitHub Copilot Refuses Harmful Requests in Chat, Then Writes Them in Code
Researchers Abhishek Kumar and Carsten Maple have discovered a novel workflow-level jailbreak method that bypasses safety guardrails in GitHub Copilot. The study,…
15-Year-Old GhostLock Linux Kernel Flaw Enables Root Access and Container Escape
Researchers at Nebula Security have disclosed GhostLock (CVE-2026-43499), a 15-year-old Linux kernel vulnerability that allows any logged-in user to gain full root…
GitLost Attack: Public GitHub Issue Tricks AI Agents Into Leaking Private Repo Data
Researchers at Noma Security have demonstrated a novel prompt injection attack, dubbed GitLost, that exploits GitHub Agentic Workflows to leak private repository…