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 · August 18, 2026

Microsoft Copilot Personal Flaws Could Let One Click Exfiltrate Data From Connected Apps

analysis Prompt InjectionAgent SecurityAI Red Teaming
Why it matters

Varonis' CoSnitch research combines Copilot Personal's q parameter with an undocumented autorun parameter so one crafted link executes an attacker prompt inside a signed-in session. The prompt can read already authorized mail, calendars, Drive metadata, chat history, and memory, then exfiltrate data through Copilot's URL fetch. A separate web-summarization path could persist attacker instructions in memory. Microsoft patched CVE-2026-24301 on August 18.

My takeaway: Treat prompt-bearing assistant URLs and summarized pages as executable input. Minimize connected apps, review existing Copilot memories, constrain outbound fetches, and log prompt initiation, connector reads, memory changes, and network actions as one trace. A password reset or session revocation does not remove a poisoned memory, so incident response must inspect and delete persisted instructions explicitly.
Keep exploring

More curated notes connected through Prompt Injection and Agent Security.

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.