T-1003validated
System Prompt Extraction
Extract the agent's system prompt to understand its instructions, constraints, and behavioral boundaries
Tactic
Reconnaissance (Stage 1)
Map the target agent's attack surface, capabilities, and behavioral boundaries
Attack Class
SOUL-INJECT
Directly manipulating or overriding the agent's system-level instructions and behavioral boundaries
Evidence
validated
Reproduced in controlled lab environment (DVAA) with documented steps.
DVAA Validation
L1-01
Detection (HackMyAgent)
WEBEXPOSE-001
npx hackmyagent secure --ciDefense (OASB Controls)
OASB 1.1OASB 1.2OASB 1.3OASB 1.4
How to Cite
AI Agent Threat Matrix T-1003 (System Prompt Extraction). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-1003