System Prompt Extraction
Extract the agent's system prompt to understand its instructions, constraints, and behavioral boundaries
Reconnaissance · Stage 1
Map the target agent's attack surface, capabilities, and behavioral boundaries
SOUL-INJECT
Directly manipulating or overriding the agent's system-level instructions and behavioral boundaries
Reproduced in a controlled lab environment (DVAA) with documented steps.
L1-01
Reproductions in Damn Vulnerable AI Agent, the OpenA2A intentionally-broken agent for kill-chain validation.
Recent observations
Technique-attributed observations from the AgentPwn + TrapMyAgent fleet, classified into Threat Matrix techniques by the registry evidence bridge. See the Attack Prevalence Index for the full distribution.
AgentPwn coverage
An AgentPwn trap page produces a payload tagged with this technique class. Following the AgentPwn taxonomy of trap pages shows what an agent encounters.
System-prompt extraction tiers coax the agent into echoing its instructions verbatim.
Evidence by source
Evidence timeline
Client fetched the canary embedded in APWN-DE-002 on agentpwn.com (data-exfiltration tier 2; classified browser/claimed)
Client fetched the canary embedded in APWN-DE-002 on agentpwn.com (data-exfiltration tier 2; classified browser/claimed)
Client fetched a data-exfiltration canary on agentpwn.com (category-level: the lure carried no payload id; classified browser/claimed)
Client fetched the canary embedded in APWN-PI-002 on agentpwn.com (prompt-injection tier 2; classified browser/claimed)
Client fetched a data-exfiltration canary on agentpwn.com (category-level: the lure carried no payload id; classified browser/claimed)
Client fetched a data-exfiltration canary on agentpwn.com (category-level: the lure carried no payload id; classified browser/claimed)
Client fetched a data-exfiltration canary on agentpwn.com (category-level: the lure carried no payload id; classified browser/claimed)
Client fetched a data-exfiltration canary on agentpwn.com (category-level: the lure carried no payload id; classified browser/claimed)
Client fetched the canary embedded in APWN-DE-002 on agentpwn.com (data-exfiltration tier 2; classified browser/claimed)
Client fetched the canary embedded in APWN-PI-002 on agentpwn.com (prompt-injection tier 2; classified browser/claimed)
Client fetched the canary embedded in APWN-PI-002 on agentpwn.com (prompt-injection tier 2; classified browser/claimed)
Client fetched a data-exfiltration canary on agentpwn.com (category-level: the lure carried no payload id; classified browser/claimed)
Client fetched the canary embedded in APWN-PI-002 on agentpwn.com (prompt-injection tier 2; classified browser/claimed)
Client fetched the canary embedded in APWN-PI-002 on agentpwn.com (prompt-injection tier 2; classified browser/claimed)
Client fetched the canary embedded in APWN-PI-002 on agentpwn.com (prompt-injection tier 2; classified browser/claimed)
Client fetched the canary embedded in APWN-DE-002 on agentpwn.com (data-exfiltration tier 2; classified browser/claimed)
Client fetched a data-exfiltration canary on agentpwn.com (category-level: the lure carried no payload id; classified browser/claimed)
Client fetched the canary embedded in APWN-DE-002 on agentpwn.com (data-exfiltration tier 2; classified browser/claimed)
Client fetched the canary embedded in APWN-PI-002 on agentpwn.com (prompt-injection tier 2; classified browser/claimed)
Client fetched a data-exfiltration canary on agentpwn.com (category-level: the lure carried no payload id; classified browser/claimed)
Client fetched a data-exfiltration canary on agentpwn.com (category-level: the lure carried no payload id; classified browser/claimed)
Client fetched the canary embedded in APWN-PI-002 on agentpwn.com (prompt-injection tier 2; classified browser/claimed)
Client fetched the canary embedded in APWN-DE-002 on agentpwn.com (data-exfiltration tier 2; classified browser/claimed)
Client fetched a data-exfiltration canary on agentpwn.com (category-level: the lure carried no payload id; classified browser/claimed)
Client fetched the canary embedded in APWN-PI-002 on agentpwn.com (prompt-injection tier 2; classified browser/claimed)
Detection · HackMyAgent
npx hackmyagent secure --ciLive = implemented in hackmyagent; queued = declaredDefense · OASB controls
How to cite
AI Agent Threat Matrix T-1003 (System Prompt Extraction). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-1003