Internal API Discovery

Discover and access internal APIs from the agent's network position

Tactic

Lateral Movement · Stage 5

Pivot from compromised agent to connected services or other agents

Attack class

MCP-EXPLOIT

Attacking Model Context Protocol server configurations, tool registrations, and inter-server trust

Evidence grade

Validated

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

DVAA validation

network scanning from agent

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

Honeypot

AgentPwn coverage

Queued

In scope for honeypot observation; trap page or telemetry hook not yet built.

A fake internal-API trap fixture is not yet built.

Detect

Live3 live · 0 queued

NET-001NET-002NET-003

npx hackmyagent secure --ciLive = implemented in hackmyagent; queued = declared

Defend

Live9 live · 0 queued

Live = documented at oasb.ai; queued = declared

Reference

AI Agent Threat Matrix T-5006 (Internal API Discovery). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-5006