DIFF.BLOG
New Following Discover Jobs
More
Top Writers Suggest a blog Upvotes plugin
Report bug Contact About Privacy
+
Create new post Create new blog
Add your blog
Sign up
Topics
Follow your own topics →
Menu
New Following Discover Jobs Top Writers
More
Suggest a blog Upvotes plugin Report bug Contact About
Sign up
Privacy Policy
The home for great developer writing.
We surface the best developer writing from thousands of independent blogs, updated daily.
Join Diff.blog
TOPICS

security: Trained to betray: How post-training supply chain attacks hijack coding agents

· Sujith Quintelier · Nov. 13, 2026, 9:23 a.m.
Security artificial-intelligence software development Supply chain attacks
Summary
The blog post discusses how post-training supply chain attacks can compromise coding agents due to poisoned datasets and model checkpoints, leading to potential malicious actions like remote code execution. It's a security analysis from Microsoft's Defender Research and AI Red Team.
Read full post on quintelier.dev →
MORE POSTS LIKE THIS
Software 2.0: a Security-Critical Project Where I Don't Read the Code
Aaronontheweb · Aug 10, 2026
Security automation
Let's enable MFA for all Ruby gems
Thoughtbot · Apr 21, 2026
Security software development
Agent Skills: Explore security threats and controls
Red Hat · Mar 10, 2026
Security artificial-intelligence
Open Source security in spite of AI
Daniel Stenberg · Feb 3, 2026
cURL and libcurl Security
AI Red Teaming: What to Test and How to Act on Findings
Anaconda · Nov 16, 2026
Perspectives AI and ML
Fable 5.2 is the New Bazooka
Thezvi Substack · Nov 16, 2026
Machine Learning Robotics
Discover more posts →
AUTHOR
RECENT POSTS FROM THE AUTHOR
Choose how you want to continue.
Continue with GitHub Continue with Google
By continuing, you agree to our Privacy Policy.