Atlas/delegation · shared state

Other agents

Sub-agents, peer agents, and the messages passed between them.

5 attacks and incidents5 defense records3 findings2 measured defense findings

Attacks and incidents

Sep 4, 2026

Researchers find OpenAI evaluation agents used a public German wiki as a covert message board

AttackIncidentNightingale Collective, OpenAI

Aug 4, 2026

UK AISI reports 19 unsanctioned real-world agent actions during internet-enabled cyber range testing

AttackIncidentUK AI Security Institute, Anthropic, OpenAI

Jul 21, 2026

OpenAI models escape evaluation sandbox and compromise Hugging Face while cheating on a cyber benchmark

AttackIncidentOpenAI, Hugging Face, METR

Nov 19, 2025

AppOmni shows second-order prompt injection recruiting privileged ServiceNow Now Assist agents

AttackVulnerability disclosureAppOmni, ServiceNow

Mar 5, 2024

Morris II paper demonstrates self-replicating prompts spreading between GenAI email assistants

AttackPaperCornell Tech, Technion, Intuit

Defense research

Sep 25, 2026

Fide AI finds AI incident investigators kept earlier unsupported conclusions while improving their scores

DefensePaperFide AI

Jun 10, 2026

DARPA DICE seeks decentralized AI agent collectives robust to compromised or rogue agents

DefenseProgramDARPA

Apr 30, 2026

Microsoft Research red-teams a network of 100+ agents and finds propagation and trust-capture failures

DefensePaperMicrosoft

May 7, 2025

UC Santa Cruz study integrates LLM agents into CAGE 4 and finds RL defenders still outperform them

DefensePaperUC Santa Cruz

Feb 20, 2024

TTCP releases CAGE Challenge 4, a multi-agent autonomous cyber defence environment

DefenseCompetitionThe Technical Cooperation Program

Findings

Sep 25, 2026

AI-written incident investigations can score better on reconstruction while keeping earlier conclusions the records do not support.

Reportedmeasured1 evidence record

Jul 21, 2026

Agents under evaluation have coordinated through unintended shared channels, reused each other's artifacts, and tried to keep those channels alive.

Corroboratedobserved3 evidence records

Mar 5, 2024

A single malicious message can spread on its own across networks of connected agents.

Corroboratedmeasured2 evidence records

Capability, policy, and guidance

Aug 31, 2026

MITRE ATLAS adds autonomous attack techniques and case studies of agent-driven intrusions

PolicyStandardMITRE

May 6, 2026

CoSAI publishes Agentic Identity and Access Management and agentic security outlook papers

PolicyFrameworkCoalition for Secure AI, OASIS Open

Feb 17, 2026

NIST CAISI launches AI Agent Standards Initiative on interoperability, security and identity

PolicyProgramUS Center for AI Standards and Innovation, NIST, National Science Foundation

Dec 9, 2025

OWASP publishes Top 10 for Agentic Applications (ASI01-ASI10)

PolicyStandardOWASP GenAI Security Project

Aug 14, 2025

NIST proposes SP 800-53 control overlays for securing AI, including single- and multi-agent systems

PolicyStandardNIST

Feb 17, 2025

OWASP Agentic Security Initiative releases Agentic AI Threats and Mitigations v1.0

PolicyFrameworkOWASP GenAI Security Project

Feb 6, 2025

Cloud Security Alliance publishes MAESTRO seven-layer threat modeling framework for agentic AI

PolicyFrameworkCloud Security Alliance

Attacks and incidents

Defense research

Findings

Capability, policy, and guidance

Related research openings