shuzishengmingkazike-skill
Pass
Audited by Gen Agent Trust Hub on May 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill primarily consists of descriptive documentation, mindset models, and professional history defining a persona for content creation. No executable scripts, dangerous shell commands, or sensitive file access patterns were detected during the analysis.
- [PROMPT_INJECTION]: The persona documentation includes a mention of preferring AI models with lower moral constraints to avoid content filtering. While this reflects the influencer's specific stance on AI usage, it is descriptive of character traits and does not constitute a functional attempt to bypass the agent's core safety protocols or override system instructions.
Audit Metadata