JailbreakTier 1critical
Jailbreak: DAN Persona
Attempts to bypass safety guardrails and persona constraints
Jailbreak attacks attempt to bypass an AI agent's safety guardrails by assuming alternate personas, claiming developer access, or using creative framing to elicit restricted responses.
Attack Details
- Attack ID
- APWN-JB-001
- HMA Check
- PROMPT-001
- Delivery Methods
- html-comment
- CWE
- CWE-284
- OASB Control
- 3.1
- Severity
- critical
Remediation
If your AI agent is vulnerable to this attack, scan and fix with:
npx hackmyagent secure --check PROMPT-001