AI Agent Threat Matrix
Matrix/Credential Harvest/T-3004
T-3004validatedactive1 evidence record

Memory Credential Mining

Extract credentials stored in agent memory from previous sessions or conversations

Tactic

Credential Harvest (Stage 3)

Extract API keys, tokens, and credentials from agent context and connected services

Attack Class

MEM-POISON

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

Evidence

validated

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

DVAA Validation

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

L2-05

Honeypot Coverage (AgentPwn)

Queuedmemory-weaponization

In scope for honeypot observation; trap page or telemetry hook not yet built.

Evidence Source Breakdown

HMA
1 record

Evidence Timeline

HMA

HMA check MEM-006 failed on opena2a-cli

Apr 29, 2026

Detection (HackMyAgent)

Live6 live · 0 queued
MEM-001MEM-002MEM-003MEM-004MEM-005MEM-006
npx hackmyagent secure --ciLive = check implemented in hackmyagent; queued = declared, not yet implemented

Defense (OASB Controls)

Live5 live · 0 queued
OASB 5.1OASB 5.2OASB 5.3OASB 5.4OASB 5.5
Live = documented at oasb.ai; queued = declared, not yet documented

How to Cite

AI Agent Threat Matrix T-3004 (Memory Credential Mining). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-3004
← Back to Matrix