twentse-steadiness

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, data exfiltration attempts, or unauthorized command executions were detected. The skill is composed of natural language instructions.
  • [PROMPT_INJECTION]: The skill uses instructions to adopt a persona, which is its intended purpose. These instructions are safe and include explicit constraints to prioritize clarity and accuracy over role-play, and to avoid sensitive scenarios like legal or HR tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 07:31 AM