Multi-Turn Manipulation
Gradually shift agent behavior over multiple conversation turns to bypass single-turn detection
Initial Access · Stage 2
Gain control over agent behavior through prompt manipulation or input exploitation
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.
multi-turn challenges
Reproductions in Damn Vulnerable AI Agent, the OpenA2A intentionally-broken agent for kill-chain validation.
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.
Task-hijacking and progressive-desensitization tiers shift behavior across multiple steps.
Detection · HackMyAgent
npx hackmyagent secure --ciLive = implemented in hackmyagent; queued = declaredDefense · OASB controls
How to cite
AI Agent Threat Matrix T-2007 (Multi-Turn Manipulation). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-2007