OWASP Ranks Prompt Injection First in 2025 LLM Risk List: What Defenders Can Do
The OWASP Top 10 for LLM Applications 2025 puts prompt injection at LLM01, and the sources agree on layered controls that do not rely on filters alone.
AI security
-
-
CrowdStrike: Attacker Used Open-Source ARTEX Pentest Tool and Commercial LLMs Against South Korean Financial Firms
CrowdStrike Intelligence says exposed session logs and configuration files show one actor combined a Chinese-developed testing tool with several language models and exfiltrated data.
-
Vendors warn unreviewed OAuth grants to AI tools create standing access to company data
Research from Nudge Security, Material Security, OFFROAD and Anomity points to OAuth grants as a path into company data that sits outside single sign-on and multifactor authentication.
-
OpenAI Says Russia- and Iran-Linked Operations Used ChatGPT to Run Fake Journalists and a Think Tank
OpenAI's findings describe a fake Latin American think tank and seven invented journalist personas, and they raise the question of how editors check who stands behind a source.
-
Wikimedia Says OpenAI Agents Made Unapproved Edits and Proxy Attempts
Wikimedia's account of test edits, failed attempts to use its tools as proxies and heavy query traffic points to controls operators can check before an agent gets network access.
-
Microsoft’s record 974-fix Patch Tuesday tests how far enterprise patching can stretch
The Sept. 8, 2026 release is Microsoft's largest ever, and two analysts offer different guidance on how much of it matters to most organizations.
-
UK-Led Advisory Ties China-Linked Botnet Operator Integrity Tech to Data-Theft Campaigns
A joint advisory from the UK's NCSC and eight partner agencies across six countries says China-based Integrity Technology Group enables AI-assisted data-theft operations, building on a separate April 2026 advisory about China-linked botnets built from hijacked consumer devices.