We collected the confirmed security incidents involving AI coding agents since July 2025. 20 so far. 13 of them started with something a developer installed: a package, an MCP server, a skill, an editor extension. Sources on every entry: node9.ai/incidents
This story is from 2026-10-20. It is preserved in the archive; the latest stories are on the live feed.
Coverage of "We collected the confirmed security incidents involving AI coding agents since July 2025. 20 so far. 13 of them started with something a developer installed: a package, an MCP server, a skill, an editor extension. Sources on every entry: node9.ai/incidents" from 1 source, with a live timeline of who reported what and when.
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-10-20 20:05 · DEV Community — AI
We collected the confirmed security incidents involving AI coding agents since July 2025. 20 so far. 13 of them started with something a developer installed: a package, an MCP server, a skill, an editor extension. Sources on every entry: node9.ai/incidents
More stories
- OpenAI acquires Orchestra Bio — OpenAI News
- DeepSeek V4.1 Flash is now available in Token Pass — Vercel Blog
- US bans DeepSeek AI from government systems: What the official notice says about ‘transfer of sensitive data’ to China — Mint AI
- Meta pauses Muse sharing after researchers find AI chats on the web — The Verge AI
- Beyond the KV cache: Training and serving i14’s Laplace 3B linear attention model on AWS Trainium2 with native PyTorch — AWS Machine Learning Blog
- Build a semantic layer for agentic AI on AWS with AtScale and Amazon Bedrock AgentCore — AWS Machine Learning Blog
- CoreWeave Completes Acquisition of Weights & Biases — CoreWeave Blog
- Liquid Cooling for AI Data Centers: Run Cold, Act Bold — CoreWeave Blog
Get the daily brief of stories like this at 6:30 every morning →