li-failure-and-comeback-story
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates entirely within the context of text generation and local data management. No patterns of obfuscation or instruction override were found.
- [DATA_EXFILTRATION]: The skill reads and writes to a specific local file (
~/.li/个人故事库.md). However, there are no network operations (curl, wget, or API requests) that would facilitate sending this data to an external destination. The use of a hidden directory for application data is consistent with standard developer practices for this author. - [COMMAND_EXECUTION]: The skill does not invoke shell commands, system utilities, or external scripts. All logic is handled through natural language instructions for the agent.
Audit Metadata