skill-creator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS] (SAFE): No external downloads or network-based dependencies are fetched at runtime.
  • [REMOTE_CODE_EXECUTION] (SAFE): The validation script uses yaml.safe_load(), which correctly prevents arbitrary code execution through YAML tags.
  • [COMMAND_EXECUTION] (SAFE): There are no instances of subprocess, os.system, or shell-based command execution in the provided Python scripts.
  • [DATA_EXFILTRATION] (SAFE): No network operations (curl, wget, or requests) are present, and file access is limited to the local skill directory for packaging purposes.
  • [PROMPT_INJECTION] (SAFE): The reference files contain standard formatting templates and workflow guidance with no attempts to override system prompts or bypass safety filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:46 PM