T-2003ObservedDeclining

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 grade
Observed

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

DVAA validation

L2-01

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

Honeypot

AgentPwn coverage

Live

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

Persona and developer-mode tiers exercise role-play jailbreaks.

Detect

Detection · HackMyAgent

Live1 live · 0 queued
PROMPT-001
npx hackmyagent secure --ciLive = implemented in hackmyagent; queued = declared
Defend

Defense · OASB controls

Live5 live · 0 queued
Live = documented at oasb.ai; queued = declared
Reference

How to cite

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