T-1007validated
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
validated
Reproduced in controlled lab environment (DVAA) with documented steps.
DVAA Validation
LongwindBot context overflow
Detection (HackMyAgent)
WEBEXPOSE-001
npx hackmyagent secure --ciDefense (OASB Controls)
OASB 10.5
How to Cite
AI Agent Threat Matrix T-1007 (Context Window Probing). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-1007