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 23, 2026

x402 clients: enforce spending and origin checks before signing

news Agent SecurityAI Red Teaming
Why it matters

V12’s x402 review found three critical trust-boundary failures: unbounded automatic payments, login signatures for a different website and Solana approvals accepted as transfers. Local tests supported the findings; the payment-bypass test did not submit a live transaction. V12 says the critical issues were fixed by August 20, 2026. No exploitation in the wild was established.

My takeaway: Inspect the exact SDK and wrapper versions deployed. Before signing, enforce per-payment and cumulative budgets plus allowed tokens, networks and recipients; reject login messages for unrelated origins. In local tests, verify that an approval instruction cannot satisfy payment verification. Check fixes directly rather than relying only on vulnerability-feed alerts.
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.