The Hacker News AI Security · November 15, 2026

Cursor incident update: exposed agent traces led to marketplace tampering

Why it matters

Cursor says a key exposed at Fireworks enabled access to historical, non-Privacy-Mode agent traces containing credentials. Further credential theft led to malicious Claude Code extensions being placed in Cursor’s marketplace cache on October 29. Its investigation identifies versions 2.1.312 and 2.1.313 during a roughly 11-hour window; Anthropic and Open VSX did not distribute those copies. The findings are vendor-reported, and uninstalling the extension may leave persistence.

My takeaway: Match installation records to Cursor’s October 29 exposure window and affected macOS or Windows packages. Use the primary notice’s hashes and persistence indicators to investigate; isolate hosts showing execution, remove unauthorized SSH keys and startup mechanisms, and rotate accessible credentials from a trusted system. Also scan retained agent traces and support exports for secrets and revoke unnecessary vendor storage access.
Keep exploring

More curated notes connected through Agent Security and AI Engineering.

OWASP GenAI Security Project · guide

OWASP Top 10 for Agentic Applications for 2026

OWASP's community guide organizes agentic-system risk into ten categories, including goal hijacking, tool misuse, identity and privilege abuse, memory poisoning, insecure inter-agent communication, cascading failures, and rogue-agent behavior. It provides a shared taxonomy and mitigation starting point rather than a certification checklist or evidence that a deployed system is secure.

OECD.AI Wonk · guide

A five-step roadmap to closing the AI evaluation gap

The roadmap addresses evaluation results that overstate real-world performance or fail to transfer across deployment contexts. Its five steps balance standardized and local tests, evaluate throughout the lifecycle, build qualified assurance and communication capacity, tailor tests to each value-chain actor and technology, and use a coordinated, trusted process for updating methods.

OWASP GenAI Security Project · tool

FinBot CTF Is Live: A Hands-On Companion to the OWASP GenAI Security Project

OWASP FinBot is a hands-on agentic-security CTF built around a simulated multi-agent financial-services platform with real tool access. Its challenges cover prompt injection, tool misuse, policy bypass, data exfiltration, privilege escalation, remote code execution, shared context, and compromised MCP servers.