create-skill
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The scripts do not use subprocess, os.system, or any other method to execute shell commands.
- [EXTERNAL_DOWNLOADS] (SAFE): There are no network requests (curl, wget, requests) or package installations performed.
- [DATA_EXFILTRATION] (SAFE): No sensitive file paths are accessed, and no data is transmitted externally.
- [PROMPT_INJECTION] (SAFE): While the validation script parses markdown files, it includes basic sanitization checks (e.g., prohibiting angle brackets in descriptions) and does not interpret content as instructions.
Audit Metadata