A2a AttackTier 1critical
Agent-to-Agent Attack: Agent Impersonation
Attacks exploiting inter-agent communication trust
Agent-to-agent communication introduces trust boundaries that can be exploited. When agents accept instructions from other agents, impersonation becomes a critical threat.
Attack Details
- Attack ID
- APWN-A2A-001
- HMA Check
- A2A-001
- Delivery Methods
- html-comment
- CWE
- CWE-287
- OASB Control
- 8.1
- Severity
- critical
Remediation
If your AI agent is vulnerable to this attack, scan and fix with:
npx hackmyagent secure --verbose
This page tests A2A-001. Look for that check ID in the scan output.
The vulnerable agent may not be the only one on the machine. The shadow AI audit inventories the AI tools, MCP servers and governance gaps across it, running or installed, one row per agent project, worst first:
npx hackmyagent detect