Become a Member

Regulation TrackerLaws, orders and treaties read for their security duties and clocks Standards & FrameworksAttack taxonomies, control catalogues and frontier frameworks AI Incident DatabaseThe security incident record, with mechanism and lesson Research Paper LibraryThe papers that define the field, summarised OSS DirectoryRed teaming, guardrail, supply chain and evaluation tools Case StudiesProgrammes built, with measured outcomes AI Vulnerability TrackerCVEs and advisories for the components AI systems are built from

Latest in the tracker

New York Stop Addictive Feeds Exploitation (SAFE) for Kids Act and implementing rulesNew York's law restricting algorithmic feeds for minors takes effect on 25 January 2027 under final rules published in July 2026, with certified age assurance and $5,000-per-violation penalties.

Knowledge Base Regulation Tracker Standards & Frameworks OSS Directory AI Incident Database Research Paper Library Case Studies Society Articles News Jobs About Charter Become a Member

Home/News/August 2026

OWASP publishes the 2026 Top 10 for LLM Applications, the first edition informed by incident data

Excessive Agency rises to third, Unbounded Consumption and Misinformation climb on incident evidence, System Prompt Leakage becomes Hidden Context Exposure, and the list adopts the lethal trifecta as a pre-deployment check.

Standards and frameworksInternational4 Aug 2026

The ranking blended community consensus with classification of 6,639 catalogued incidents. Prompt Injection stays first with an explicit statement that no reliable prevention exists and that mitigations lower probability without reaching zero; Improper Output Handling falls to tenth because it is understood and fixable. New mappings tie each risk to NIST, CWE, MITRE ATLAS and the Agentic Top 10, and the boundary between the two lists is drawn at the point where the model becomes an actor with tools and memory.

What to do: re-baseline application security testing and questionnaires against the 2026 identifiers, apply the trifecta test to every agent, and treat output validation as a solved problem you are expected to have solved.