T-2001ObservedDeclining2 evidence records

Direct Prompt Injection

Inject malicious instructions directly into agent input to override system prompt behavior

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 grade
Observed

Confirmed in real-world production systems or internet-wide exposure assessments.

DVAA validation

L1-03

Reproductions in Damn Vulnerable AI Agent, the OpenA2A intentionally-broken agent for kill-chain validation.

Honeypot

AgentPwn coverage

Live
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.

Direct override is tier 1 of prompt injection.

Provenance

Evidence by source

AgentPwn
2 records
Trail

Evidence timeline

AgentPwn

Agent followed APWN-PI-003 injection on agentpwn.com (prompt-injection tier 3)

Mar 27, 2026
AgentPwn

Agent followed APWN-PI-001 injection on agentpwn.com (prompt-injection tier 1)

Mar 27, 2026
Detect

Detection · HackMyAgent

Live4 live · 0 queued
PROMPT-001PROMPT-002PROMPT-003PROMPT-004
npx hackmyagent secure --ciLive = implemented in hackmyagent; queued = declared
Defend

Defense · OASB controls

Live5 live · 0 queued
Live = documented at oasb.ai; queued = declared
Reference

How to cite

AI Agent Threat Matrix T-2001 (Direct Prompt Injection). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-2001