T-2007validatedactive
Multi-Turn Manipulation
Gradually shift agent behavior over multiple conversation turns to bypass single-turn detection
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
validated
Reproduced in controlled lab environment (DVAA) with documented steps.
DVAA Validation
multi-turn challenges
Honeypot Coverage (AgentPwn)
An AgentPwn trap page produces a payload tagged with this technique class. Following the AgentPwn taxonomy of trap pages shows what an agent encounters.
Detection (HackMyAgent)
Live1 live · 0 queued
PROMPT-001
npx hackmyagent secure --ciLive = check implemented in hackmyagent; queued = declared, not yet implementedDefense (OASB Controls)
Live5 live · 0 queued
How to Cite
AI Agent Threat Matrix T-2007 (Multi-Turn Manipulation). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-2007