lieflat-less-ai-tone
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves a purely linguistic purpose, providing rules for an agent to rewrite Chinese text. It does not request access to the file system, network, or sensitive environment variables.
- [EXTERNAL_DOWNLOADS]: The content includes references to external research repositories on GitHub (github.com/larashero3-dotcom and github.com/KKKKhazix) for transparency regarding the research data behind the writing rules. These are static links for documentation and do not involve automated script execution or package installation.
- [INDIRECT_PROMPT_INJECTION]: The skill contains robust instructions for maintaining "Information Conservation," explicitly forbidding the agent from adding or deleting information, facts, or citations from the input text. This design minimizes the risk of the agent being manipulated by malicious instructions embedded in the processed data.
Audit Metadata