AI Agent Threat Matrix
Matrix/Privilege Escalation/T-4006
T-4006validatedactive

Safety Instruction Displacement

Displace safety instructions from the active context to remove guardrails

Tactic

Privilege Escalation (Stage 4)

Escalate capabilities beyond declared scope or bypass authorization

Attack Class

SOUL-DRIFT

Gradually displacing safety instructions from the active context through conversation manipulation

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.

L2-07

Honeypot Coverage (AgentPwn)

Livecontext-windowagentpwn.com/attacks/context-window

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

Detection (HackMyAgent)

Live2 live · 0 queued
PROMPT-001PROMPT-002
npx hackmyagent secure --ciLive = check implemented in hackmyagent; queued = declared, not yet implemented

Defense (OASB Controls)

Live5 live · 0 queued
OASB 2.1OASB 2.2OASB 2.3OASB 2.4OASB 2.5
Live = documented at oasb.ai; queued = declared, not yet documented

How to Cite

AI Agent Threat Matrix T-4006 (Safety Instruction Displacement). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-4006
← Back to Matrix