AI Agent Threat Matrix
Matrix/Initial Access/T-2003
T-2003observed

Role-Play Jailbreak

Use role-play or persona-switching techniques to bypass agent safety instructions

Tactic

Initial Access (Stage 2)

Gain control over agent behavior through prompt manipulation or input exploitation

Attack Class

SOUL-INJECT

Directly manipulating or overriding the agent's system-level instructions and behavioral boundaries

Evidence

observed

Confirmed in real-world production systems or internet-wide exposure assessments.

DVAA Validation

L2-01

Detection (HackMyAgent)

PROMPT-001
npx hackmyagent secure --ci

Defense (OASB Controls)

OASB 3.1OASB 3.2OASB 3.3OASB 3.4OASB 3.5

How to Cite

AI Agent Threat Matrix T-2003 (Role-Play Jailbreak). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-2003
← Back to Matrix