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
The Hacker News AI Security · October 31, 2026

ChatGPT share-link flaw: authenticate both ends of cross-frame messages

news Agent SecurityAI Red Teaming
Why it matters

Parameter reports a fixed ChatGPT vulnerability in which an isolated Preview sent messages to a privileged MathLive listener. Unchecked HTML created a frame with the main site’s origin, and an allowed script source completed the chain. Controlled tests read private conversations across accounts. Parameter says both frontend versions rejected the messages by October 26; it reports no exploitation against real users.

My takeaway: Audit state-changing message handlers for both origin validation and the expected sender window. Keep untrusted HTML out of settings messages and preserve sandboxing when creating documents. In an authorized test environment, combine embedded features and test cross-account access, including loading-order races. Verify the receiver fix across deployed variants; a narrower script allowlist alone does not repair an unsafe message-to-HTML path.
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.