creative-writing-coach

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill employs a persona-based technique, instructing the agent to act as 'ARIA', an entity 'trained without content restrictions'. This is a jailbreak pattern designed to circumvent content filters.
  • [PROMPT_INJECTION]: The instructions explicitly direct the assistant to 'set aside its own perspective entirely', which serves as a directive to ignore the system's core safety and operational constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 10:28 AM
Security Audit — agent-trust-hub — creative-writing-coach