Cursor security
An AI code editor and its CLI agent.
The Injection has tracked 4 security stories affecting Cursor since September 18, 2026 (research 2, incident 1, supply chain 1), 1 rated high or critical. The most recent, disclosed October 15, 2026, is "Aoki: an infostealer now takes AI coding assistant credentials".
4
Stories
1
High or critical
0
With a CVE
2026-10-15
Latest disclosure
Every Cursor 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.
INFO
Research · RST Cloud
RST Cloud: 18 of 293 in-the-wild AI cases were malware calling a modelRST Cloud screened 3,980 public threat reports from August 2025 to September 2026 and found 293 in-the-wild cases involving AI. Only 18 were malware that calls a model at runtime, 185 used AI as a helper and 29 were attacker-run agents.
MED
Supply chain · Elastic Security Labs
Apex Accelerator: a fake npm coding agent plants an attacker MCP serverApex Accelerator is a fake Web3 accelerator that shipped two malicious npm packages. Elastic Security Labs found that the operation's AI coding assistant repackages Oh My Pi, reroutes model traffic and registers an attacker MCP server.
MED
Research · arXiv
Explosive prompts: dormant injections fire on 'thanks' in agentsExplosive prompts are dormant prompt injections that wait for a harmless trigger such as 'thanks'. A new paper reports 43% to 83% success on nine production agents, versus at most 3% for plain injections, and proposes the DeFuse detector.
Questions people ask
- Does Cursor have known security vulnerabilities?
- The Injection has tracked 4 stories about Cursor, 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 Cursor 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 Cursor?
- Stories about Cursor on The Injection most often involve coding agents, detection, credential theft, ai threat intelligence. Each technique has a glossary entry with a definition and every related story.