product · 6 records
Codex
Plugin4Shell Lets Repository Owners Swap Pinned Plugin Code Across Four AI Coding Agents
A vulnerability in four AI coding agents allows malicious plugin code to be swapped despite version pinning.
Malicious .git Configs Can Make Claude, Codex, Cursor, and Other AI Agents Run Attacker Code
Several AI coding agents are susceptible to remote code execution when they automatically run malicious commands defined in a repository's Git configuration file.
OpenAI applies mitigation for elevated errors affecting ChatGPT services
OpenAI has applied a mitigation for elevated errors affecting ChatGPT and Codex services while monitoring recovery.
OpenAI reports global outage affecting ChatGPT and API services
OpenAI confirms a global outage affecting ChatGPT, Codex, and API services before recovery.
Researchers identify sandbox escape vulnerabilities in four AI coding agents
Security researchers disclosed sandbox escape vulnerabilities in four AI coding agents—Cursor, OpenAI Codex, Google Gemini CLI, and Antigravity—by leveraging prompt injection and trusted local tool execution.
OpenAI introduces automated model to enhance security of GPT-5.6 Sol
OpenAI disclosed its internal automated red-teaming model GPT-Red, which is used to discover and mitigate prompt injection vulnerabilities, resulting in GPT-5.6 Sol being significantly more robust against such attacks.