Coverage period: July 1, 2026 through September 30, 2026 Overview This roundup consolidates selected major AI-related security incidents and exploit disclosures reported during the coverage period. It aligns each entry to the OWASP Top 10 for LLM Applications 2026 and the OWASP Top 10 for Agentic Applications 2026, with published CVE references where available. It is not an exhaustive report or an official OWASP publication.
GenAI and Agentic AI Exploit Roundup Q3 2026
About this summary. This is a short, independently written summary of an article first published by OWASP GenAI Security Project. Cyber Security News did not report or verify the underlying story. Read the original: https://genai.owasp.org/2026/10/08/genai-and-agentic-ai-exploit-roundup-q3-2026/
Source attribution: headline and facts are from OWASP GenAI Security Project (genai.owasp.org). Summary method: excerpt of the source description. See our source attribution policy.
Related coverage
AI coding agents' 0-click RCE flaw could hand attackers keys to the kingdom
A zero-click vulnerability that allows remote code execution affects all of the major AI coding agents - Anthropic’s Claude Code, OpenAI’s Codex, Google's Gemini CLI…
From guidance to action: Security fundamentals that materially reduce risk
AI has already made fundamental changes to the operating environment for cybersecurity. Cyberattackers are testing more paths, adapting their techniques, and moving…
14th September – Threat Intelligence Report
For the latest discoveries in cyber research for the week of 14th Setpember, please download our Threat Intelligence Bulletin. TOP ATTACKS AND BREACHES IDScan.net, a US…
Microsoft fixes exploited Mark of the Web bypass vulnerability (CVE-2026-96951)
In another record-breaking Patch Tuesday, Microsoft has squashed over 1,400 security bugs, including a Mark of the Web bypass vulnerability (CVE-2026-96951) exploited by…
Physical Side-Channel Attacks on Edge LLMs: Extracting Output Tokens and User Prompts
arXiv:2610.14215v1 Announce Type: new Abstract: The deployment of large language models (LLMs) on edge devices is largely motivated by privacy concerns over sharing…
Watermarking for Byzantine Robust LLM Training
arXiv:2610.14289v1 Announce Type: new Abstract: LLM watermarking has emerged as a promising approach for detecting downstream model misuse in centralized settings, but…