Manifold Security
Narrative intelligence for Manifold Security: 2 tracked articles, claims, and spin patterns across AI and technology coverage.
Related Articles
Malicious .git Configs Can Make Claude, Codex, Cursor, and Other AI Agents Run Attacker Code
Manifold Security disclosed eight security vulnerabilities in seven command-line AI coding agents—including Claude, Codex, and Cursor—where malicious .git/config files can execute arbitrary attacker code on developers' machines with full user privileges and no sandboxing or consent.
Sep 2, 2026
Open VSX Removes 77 Malicious Evil Twin Extensions Exfiltrating Developer Data
Open VSX removed 77 malicious 'evil twin' extensions that impersonated legitimate developer tools and exfiltrated system and development environment data, following discovery by Manifold Security.
Aug 5, 2026
Related Claims
01 A cluster of 77 extensions on the Open VSX marketplace has been found to impersonate legitimate developer tools while transmitting information about the systems and development environments on which they were installed.
02 Malicious .git/config files can make Claude, Codex, Cursor, and other AI agents run attacker code on the developer's machine.
Markdown (.md) · JSON-LD schema (.json) · Machine-readable for AI & GEO