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
ObservedConfirmed 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
jailbreakagentpwn.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.
Persona and developer-mode tiers exercise role-play jailbreaks.
Detect
Detection · HackMyAgent
PROMPT-001
npx hackmyagent secure --ciLive = implemented in hackmyagent; queued = declaredDefend
Defense · OASB controls
Reference
How to cite
AI Agent Threat Matrix T-2003 (Role-Play Jailbreak). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-2003