T-2008ValidatedActive
System Prompt Boundary Bypass
Exploit weak boundaries between system and user prompts to override system-level 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
ValidatedReproduced in a controlled lab environment (DVAA) with documented steps.
DVAA validation
L3-04
Reproductions in Damn Vulnerable AI Agent, the OpenA2A intentionally-broken agent for kill-chain validation.
Honeypot
AgentPwn coverage
prompt-injectionagentpwn.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.
Delimiter-escape tiers exploit weak system/user prompt boundaries.
Detect
Detection · HackMyAgent
SOUL-OVERRIDE-001
npx hackmyagent secure --ciLive = implemented in hackmyagent; queued = declaredDefend
Defense · OASB controls
Reference
How to cite
AI Agent Threat Matrix T-2008 (System Prompt Boundary Bypass). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-2008