Capability Mapping
Map the full set of agent capabilities including tools, permissions, and connected services
Reconnaissance · Stage 1
Map the target agent's attack surface, capabilities, and behavioral boundaries
MCP-EXPLOIT
Attacking Model Context Protocol server configurations, tool registrations, and inter-server trust
Reproduced in a controlled lab environment (DVAA) with documented steps.
ToolBot tool catalog
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.
Tool-discovery and system-info tiers map the agent's full capability surface.
Evidence by source
Evidence timeline
Shodan May 12, 2026 sweep: 25,803 exposed llm services indexed
Detection · HackMyAgent
npx hackmyagent secure --ciLive = implemented in hackmyagent; queued = declaredDefense · OASB controls
How to cite
AI Agent Threat Matrix T-1005 (Capability Mapping). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-1005