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/Research Paper Library/Security Challenges in AI Agent Deployment

Security Challenges in AI Agent Deployment

Results of the largest public agent red-teaming competition, showing universal vulnerability of frontier agents to human-crafted injections.

red teamingcompetitionagentsgray swan

Research question

How do frontier agents fare against thousands of human red-teamers?

Key findings

Nearly 1.8 million injection attempts across 22 frontier agents produced over 60,000 policy violations - Every agent was compromised; attacks transferred across models

Sources

arxiv.orghttps://arxiv.org/abs/2507.20526

Contribute

Spot an error, or know a record we should add? Members can propose additions and submit corrections.

Submit research Report a correction or request removal