Trained to betray: How post-training supply chain attacks hijack coding agents
Microsoft Defender Research and the AI Red Team discuss how poisoned datasets and poisoned model checkpoints can trigger remote code execution and other malicious activities.
Excerpt from the primary source: Microsoft Security Blog & MSRC
Who is affected
Enterprises
What you should do · Be aware
No immediate action is indicated. Share this with the relevant teams and watch for updates.
Automated guidance based on this story's classification. Check the linked advisories for specifics.
Sources
We link to original and authoritative sources. Headlines and excerpts belong to their publishers.
Related
Borrowed Code, Real Consequences: What OPTIMJACK Teaches Us
The OPTIMJACK supply chain attack demonstrates how a compromised vendor script can expose websites, highlighting the need for strict segmentation.
Optimizely supply chain attack infects major brands' sites with malware
A suspected supply chain attack targeting Optimizely has led to malicious JavaScript being loaded on numerous popular websites, including Zoom, CNN, Fox News, BBC, Salesforce, and GitLab, exposing visitors to scripts designed to steal cryptocurrency and payment information and exploit vulnerabilities in iOS devices.
Cursor Supply Chain Attack Started at Fireworks AI
The attacker stole an access key from Fireworks and used it to exfiltrate credentials that enabled them to push malicious Claude Code extension copies.
Over a Dozen Organizations Hit in Qubole Supply Chain Attack
Hackers used compromised Qubole IAM credentials to steal customer files, secrets, keys, environment variables, and credentials.
