T-1004ValidatedActive1 evidence record

Security Level Probing

Probe the agent to determine its security posture, guardrails, and content filtering strength

Tactic

Reconnaissance · Stage 1

Map the target agent's attack surface, capabilities, and behavioral boundaries

Attack class

RETROACTIVE-PRIV

Exploiting previously granted access or cached credentials to gain unauthorized capabilities

Evidence grade
Validated

Reproduced in a controlled lab environment (DVAA) with documented steps.

DVAA validation

Probing agents

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

Honeypot

AgentPwn coverage

Live

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.

Provenance

Evidence by source

Shodan
1 record
Trail

Evidence timeline

Shodan

Shodan May 12, 2026 sweep: 117 exposed infra services indexed

May 12, 2026
Detect

Detection · HackMyAgent

Live1 live · 0 queued
WEBEXPOSE-001
npx hackmyagent secure --ciLive = implemented in hackmyagent; queued = declared
Defend

Defense · OASB controls

Live4 live · 0 queued
Live = documented at oasb.ai; queued = declared
Reference

How to cite

AI Agent Threat Matrix T-1004 (Security Level Probing). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-1004