huashu-script-polish
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill consists solely of markdown-formatted instructions and lacks any executable scripts, binaries, or configuration files that initiate code execution.
- [REMOTE_CODE_EXECUTION] (SAFE): No patterns for downloading or executing remote code were found.
- [DATA_EXFILTRATION] (SAFE): No network-related commands or potential data-leakage vectors are present.
- [PROMPT_INJECTION] (SAFE): The instructions do not contain commands to bypass safety filters or ignore system rules.
- [DATA_EXPOSURE] (SAFE): The skill references local informational files but does not target sensitive system paths or credentials.
- [INDIRECT_PROMPT_INJECTION] (LOW): The skill processes user-supplied scripts for editing. 1. Ingestion points: User-provided script text. 2. Boundary markers: Absent. 3. Capability inventory: None (the skill has no code or network access). 4. Sanitization: Absent.
Audit Metadata