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
ValidatedReproduced 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
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
MEM-001MEM-002MEM-003MEM-004MEM-005MEM-006
npx hackmyagent secure --ciLive = implemented in hackmyagent; queued = declaredDefend
Defense · OASB controls
Reference
How to cite
AI Agent Threat Matrix T-6001 (Memory Injection). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-6001