huashu-prompt-save
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill is entirely composed of natural language instructions and organizational rules. It does not contain any executable scripts, binaries, or external code dependencies.
- [SAFE]: A thorough analysis reveals no evidence of prompt injection, data exfiltration, or obfuscation. The skill's logic is transparent and focuses solely on processing text data into a local directory structure.
- [COMMAND_EXECUTION]: While the skill involves file management (creating markdown files and updating an index), these operations are described as standard agent behaviors for data storage and are not executed via untrusted shell commands or external scripts.
Audit Metadata