li-lifetime-story
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates entirely through prompt-based interaction and local file system management. It implements a persistence mechanism by reading from and writing to
~/.li/个人故事库.md, which is a dedicated directory for the skill's data. This behavior is beneficial for user experience and does not involve any unauthorized data access. - [DATA_EXFILTRATION]: The skill does not contain any network-reaching commands or instructions to send data to external URLs. All information remains within the user's controlled local environment.
- [REMOTE_CODE_EXECUTION]: There are no external dependencies, script downloads, or dynamic code execution patterns. The logic is strictly instructional for the AI agent.
Audit Metadata