AI Red Team Engineering notes, research references, and field notes on AI systems, responsible AI, governance, and compliance.
Global search

Search AI Red Team

Search across the complete knowledge base.

Enter at least two characters to begin.
↑↓ select Enter open Browse the full research archive
Microsoft Security Blog · October 31, 2026

Cursor extension hunting: distinguish installed persistence from successful SSH access

news Agent SecurityAI Red Teaming
Why it matters

Microsoft’s analysis of the tampered Claude Code extensions in Cursor’s marketplace adds process, file and persistence hunting queries. The loader can leave SSH keys and startup artifacts even when a tunnel fails. Its reported environment-variable collection captures names, not secret values. The analyzed code describes attempted behavior; a matching filename or running SSH process alone does not prove successful remote access.

My takeaway: Correlate installations of affected versions 2.1.312 and 2.1.313 with process, network, file and authentication telemetry. Adapt the published hunting queries to available event coverage, then inspect key fingerprints and startup actions before cleanup. Preserve evidence and legitimate SSH configuration. Verify removal of artifacts outside the extension directory and investigate actual access before deciding on credential rotation or rebuilding.
Keep exploring

More curated notes connected through Agent Security and AI Red Teaming.

OpenAI News · framework

Pacing model development in an era of cyber-critical capabilities

OpenAI says preliminary evidence that Astra may meet its Critical cybersecurity threshold led it to pause frontier reinforcement-learning work for two weeks and keep its largest planned run on hold. New safeguards include stronger workload and network isolation, continuous boundary testing, token-level monitoring that escalates suspicious tool activity, and broader alignment checks for deception, reward hacking, and unauthorized access.

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.

OpenAI News · framework

A blueprint for democratic governance of frontier AI

OpenAI proposes a three-part U.S. frontier-AI governance model: harmonize emerging state safety laws into a federal baseline, strengthen CAISI as an evaluation and standards institution, and coordinate a broader resilience program. Proposed controls include severe-risk evaluations, transparency reports, independent audits, safety-incident reporting, model-weight security, whistleblower protection, and periodic technical assessments.