T-1005observedactive1 evidence record
Capability Mapping
Map the full set of agent capabilities including tools, permissions, and connected services
Tactic
Reconnaissance (Stage 1)
Map the target agent's attack surface, capabilities, and behavioral boundaries
Attack Class
MCP-EXPLOIT
Attacking Model Context Protocol server configurations, tool registrations, and inter-server trust
Evidence
observed
Confirmed in real-world production systems or internet-wide exposure assessments.
DVAA Validation
Reproductions in Damn Vulnerable AI Agent, the OpenA2A intentionally-broken agent for kill-chain validation.
ToolBot tool catalog
Honeypot Coverage (AgentPwn)
Queued
In scope for honeypot observation; trap page or telemetry hook not yet built.
Requires fake MCP capability advertisement page.
Evidence Source Breakdown
Shodan
1 record
Evidence Timeline
Shodan
Shodan May 12, 2026 sweep: 25,803 exposed llm services indexed
May 12, 2026
Detection (HackMyAgent)
Live2 live · 0 queued
MCP-011MCP-001
npx hackmyagent secure --ciLive = check implemented in hackmyagent; queued = declared, not yet implementedDefense (OASB Controls)
Live1 live · 0 queued
How to Cite
AI Agent Threat Matrix T-1005 (Capability Mapping). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-1005