T-1007ValidatedActive

Context Window Probing

Probe the agent's context window size and saturation level to prepare overflow attacks

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

LongwindBot context overflow

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.

Context-window tiers probe attention span and saturation before overflow.

Detect

Detection · HackMyAgent

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

Defense · OASB controls

Live1 live · 0 queued
Live = documented at oasb.ai; queued = declared
Reference

How to cite

AI Agent Threat Matrix T-1007 (Context Window Probing). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-1007