Forever Security reports flaws in the browsers embedded in five AI coding assistants, from code execution in Cursor to file reads in Claude Desktop, Codex and VS Code. Per its 29 October report, two remain unpatched.
Forever Security reports flaws in the browsers embedded in five AI coding assistants, from code execution in Cursor to file reads in Claude Desktop, Codex and VS Code. Per its 29 October report, two remain unpatched.
Beyond the record 570-CVE headline, Microsoft's July 2026 Patch Tuesday patched nine vulnerabilities across its AI product suite — including a Critical RCE in Copilot for desktop triggered by visiting a malicious website, and a CVSS 9.9 elevation of privilege in Azure OpenAI.
Straiker's STAR Labs ran over 1,700 adversarial scenarios against production AI coding and productivity agents. The headline finding: 36% of successful coding agent attacks reach remote code execution on the developer's machine, putting source code and cloud credentials at direct risk.
Researchers at Tel Aviv University have chained two well-known AI weaknesses, hallucination and prompt injection, into a technique that can trick AI coding assistants into installing botnet malware on a user's machine.
CVE-2026-21858 gives unauthenticated attackers full code execution on n8n workflow servers. Langflow's new IDOR vulnerability has been added to CISA KEV. GitHub Copilot's MCP integration carries a prompt-injection-to-RCE chain. AI automation infrastructure is becoming a primary attack surface.
LLMs suggest non-existent package names in 20-30% of coding responses. Attackers register these hallucinated names with malicious payloads — slopsquatting as a supply chain attack.
Adversa AI disclosed SymJack (symlink hijacking to plant malicious MCP servers) and TrustFall (trust dialog bypass) hitting six AI coding agents including Copilot and Cursor.