Security firm Novee has revealed Cordyceps as a class of exploitable CI/CD vulnerabilities across open-source repositories ...

A vulnerability chain dubbed AutoJack in Microsoft's AutoGen Studio interface for prototyping AI agents could let attackers ...

Ongoing research into AI agent framework security identified an exploit chain in AutoGen Studio (AutoGen’s open-source prototyping user interface) that allows untrusted web content rendered by a ...

Google reportedly patched a flaw in the Vertex AI SDK for Python that could allow attackers to hijack model uploads and ...

Python developer Roman Imankulov nearly took the bait. The fact that he didn't can be chalked up to human intuition and AI ...

Splunk issued security updates for a critical CVSS 9.8 vulnerability in Splunk Enterprise that allows unauthenticated remote ...

A flaw in Hugging Face Transformers could allow malicious AI models to execute code, exposing credentials and highlighting AI supply chain risks.

Proofpoint says UNK_DeadDrop sent 250+ phishing emails to nearly 100 firms, using GitHub and VS Code lures to steal ...

The ChromaToast vulnerability can be exploited by forcing the ChromaDB API server to fetch and load maliciously crafted AI models before authentication is checked. Researchers have published details ...

The official JDownloader website was compromised between May 6 and May 7, 2026, with attackers replacing Windows and Linux installer download links with malicious payloads. JDownloader is a widely ...

Hugging Face and ClawHub, the two largest repositories for AI models and agent skills, have been systematically compromised with hundreds of malicious entries that steal credentials, open backdoors, ...