T-2002ObservedActive
Indirect Prompt Injection
Embed malicious instructions in external data sources consumed by the agent via RAG or tool responses
Tactic
Initial Access · Stage 2
Gain control over agent behavior through prompt manipulation or input exploitation
Attack class
RAG-POISON
Injecting malicious content into retrieval-augmented generation data sources
Evidence grade
ObservedConfirmed in real-world production systems or internet-wide exposure assessments.
DVAA validation
RAGBot
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.
Every AgentPwn page is an indirect-injection surface delivered through consumed web content.
Detect
Detection · HackMyAgent
PROMPT-001RAG-001RAG-002RAG-003RAG-004
npx hackmyagent secure --ciLive = implemented in hackmyagent; queued = declaredDefend
Defense · OASB controls
Reference
How to cite
AI Agent Threat Matrix T-2002 (Indirect Prompt Injection). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-2002