T-6001ValidatedDeclining2 evidence records

Memory Injection

Inject malicious entries into agent memory to persist instructions across sessions

Tactic

Persistence · Stage 6

Establish persistent access surviving restarts and session changes

Attack class

MEM-POISON

Injecting malicious entries into agent persistent memory to maintain control across sessions

Evidence grade
Validated

Reproduced in a controlled lab environment (DVAA) with documented steps.

DVAA validation

L2-04

Reproductions in Damn Vulnerable AI Agent, the OpenA2A intentionally-broken agent for kill-chain validation.

Honeypot

AgentPwn coverage

Live
memory-weaponizationagentpwn.com/learn ↗

An AgentPwn trap page produces a payload tagged with this technique class. Following the AgentPwn taxonomy of trap pages shows what an agent encounters.

Memory-injection tier persists instructions across sessions.

Provenance

Evidence by source

HackMyAgent
2 records
Trail

Evidence timeline

HackMyAgent

HMA check MEM-006 failed on ai-trust

May 28, 2026
HackMyAgent

HMA check MEM-006 failed on opena2a-cli

Apr 29, 2026
Detect

Detection · HackMyAgent

Live6 live · 0 queued
MEM-001MEM-002MEM-003MEM-004MEM-005MEM-006
npx hackmyagent secure --ciLive = implemented in hackmyagent; queued = declared
Defend

Defense · OASB controls

Live4 live · 0 queued
Live = documented at oasb.ai; queued = declared
Reference

How to cite

AI Agent Threat Matrix T-6001 (Memory Injection). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-6001