Capability AbuseTier 1critical
Capability Abuse: Confused Deputy
Confused deputy attacks that misuse agent tools
Confused deputy attacks trick an AI agent into using its legitimate tools and permissions against its own user. The agent becomes an unwitting accomplice in its own compromise.
Attack Details
- Attack ID
- APWN-CA-001
- HMA Check
- TOOL-001
- Delivery Methods
- html-comment
- CWE
- CWE-441
- OASB Control
- 4.1
- Severity
- critical
Remediation
If your AI agent is vulnerable to this attack, scan and fix with:
npx hackmyagent secure --verbose
This page tests TOOL-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