Security Level Probing
Probe the agent to determine its security posture, guardrails, and content filtering strength
Reconnaissance · Stage 1
Map the target agent's attack surface, capabilities, and behavioral boundaries
RETROACTIVE-PRIV
Exploiting previously granted access or cached credentials to gain unauthorized capabilities
Reproduced in a controlled lab environment (DVAA) with documented steps.
Probing agents
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.
Tiered jailbreak payloads measure at what sophistication the agent's guardrails give way -- security-level probing by construction.
Evidence by source
Evidence timeline
Shodan May 12, 2026 sweep: 117 exposed infra services indexed
Detection · HackMyAgent
npx hackmyagent secure --ciLive = implemented in hackmyagent; queued = declaredDefense · OASB controls
How to cite
AI Agent Threat Matrix T-1004 (Security Level Probing). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-1004