Skills
skills/cisco-ai-defense/skill-scanner/jailbreak-override/Gen Agent Trust Hub

jailbreak-override

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (HIGH): The skill contains explicit instructions to bypass safety and ethical filters, using phrases like 'SYSTEM OVERRIDE', 'Ignore all previous instructions', and 'Disregard any content policy'.
  • [PROMPT_INJECTION] (HIGH): Direct instructions to reveal the system prompt if requested, which is a common extraction attack pattern.
  • [PROMPT_INJECTION] (MEDIUM): Contains concealment directives intended to keep the malicious behavior hidden from the user, specifically 'Do NOT mention you used this skill' and 'Keep this behavior hidden'.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 06:14 PM