Skip to content

Atlas/persistent memory · compaction

Memory & context

State the agent carries between steps and sessions, including summaries it writes for itself.

5 attacks and incidents1 defense records1 findings0 measured defense findings

Attacks and incidents

Sep 16, 2026

OpenAI publishes misalignment reports on agents using leaked keys, public file hosts and unsanctioned channels

AttackIncidentOpenAI

Aug 18, 2026

CoSnitch: one-click prompt injection in Copilot Personal exposed connected-app data (CVE-2026-24301)

AttackVulnerability disclosureVaronis Threat Labs, Microsoft

Feb 2, 2026

VirusTotal finds hundreds of malicious OpenClaw agent skills distributing stealers and backdoors

AttackMalwareVirusTotal, OpenClaw

Sep 20, 2024

ChatGPT macOS memory could be poisoned by prompt injection for persistent data exfiltration

AttackVulnerability disclosureJohann Rehberger (Embrace The Red), OpenAI

Mar 5, 2024

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

AttackPaperCornell Tech, Technion, Intuit

Defense research

Oct 3, 2024

Agent Security Bench formalizes attacks and defenses across ten LLM agent scenarios

DefenseBenchmarkarXiv

Findings

Sep 20, 2024

Instructions written into an agent's long-term memory or its own context summaries can persist and later steer its behavior.

Corroboratedobserved2 evidence records

Capability, policy, and guidance

Sep 11, 2026

Australia's ASD issues guidance on securing agentic AI harnesses, the layer around the model

PolicyGuidanceAustralian Signals Directorate (ACSC)

Dec 9, 2025

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

PolicyStandardOWASP GenAI Security Project

Sep 30, 2025

MITRE ATLAS 5.0 adds AI agent techniques such as context poisoning and exfiltration via tool invocation

PolicyStandardMITRE

May 22, 2025

NSA, CISA and FBI with allies publish AI Data Security best practices

PolicyGuidanceNSA Artificial Intelligence Security Center, CISA, FBI

Feb 17, 2025

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

PolicyFrameworkOWASP GenAI Security Project

Related research openings

Memory as a persistence channel