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 --check TOOL-001