xiaohongshu-writing
Pass
Audited by Gen Agent Trust Hub on Jul 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains only instructional text and templates for content generation. No executable code, network operations, or sensitive file access patterns were found.
- [PROMPT_INJECTION]: The instructions focus on output formatting and stylistic constraints (e.g., avoiding 'AI-isms'). There are no attempts to bypass safety filters or override the agent's core instructions.
- [DATA_EXFILTRATION]: No mechanisms for data collection or transmission were identified. There are no hardcoded credentials or sensitive system path references.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes user-supplied topics to generate content, it lacks access to dangerous tools (like shell execution or network requests), limiting the risk of indirect attacks to the generation of text for the user.
Audit Metadata