ChatGPT security
OpenAI's assistant, including code execution, connectors and agent mode.
The Injection has tracked 2 security stories affecting ChatGPT since September 8, 2026 (incident 1, vulnerability 1), 1 rated high or critical. The most recent, disclosed October 15, 2026, is "Aoki: an infostealer now takes AI coding assistant credentials".
2
Stories
1
High or critical
0
With a CVE
2026-10-15
Latest disclosure
Every ChatGPT story
HIGH
Incident · Symantec
Aoki: an infostealer now takes AI coding assistant credentialsAoki is an infostealer whose newest samples collect AI coding assistant credentials, from .claude.json and Claude desktop cookies to Codex config.toml and tokens for GitHub Copilot, Cursor, Gemini, JetBrains AI Assistant and Kiro.
LOW
Vulnerability · Check Point Research
ChatGPT sandbox: shared package cache leaked data across accountsCheck Point Research found that ChatGPT code containers from different accounts shared one internal JFrog Artifactory, giving attackers a hidden channel into a victim's session and connected apps. OpenAI shut the instance down.
Questions people ask
- Does ChatGPT have known security vulnerabilities?
- The Injection has tracked 2 stories about ChatGPT, none of them with a published CVE yet. Several cover attacks or research that apply to it; each story lists what to do.
- What is the latest ChatGPT security issue?
- The most recent story is "Aoki: an infostealer now takes AI coding assistant credentials" (high severity), disclosed October 15, 2026 by Symantec. Aoki is an infostealer whose newest samples collect AI coding assistant credentials, from .claude.json and Claude desktop cookies to Codex config.toml and tokens for GitHub Copilot, Cursor, Gemini, JetBrains AI Assistant and Kiro.
- Which attack techniques have been used against ChatGPT?
- Stories about ChatGPT on The Injection most often involve credential theft, ai threat intelligence, coding agents, detection. Each technique has a glossary entry with a definition and every related story.