The Agent Skills Directory

[Prompt Injection] (SAFE): Documentation files provide benign output templates and workflow examples; no jailbreak or bypass instructions were found.\n- [Data Exposure & Exfiltration] (SAFE): The packaging utility (package_skill.py) operates locally to archive skill folders and does not access sensitive system files or make network calls.\n- [Unverifiable Dependencies] (SAFE): Scripts rely on the standard library and the well-known PyYAML library. No remote code fetching was detected.\n- [Dynamic Execution] (SAFE): Metadata parsing in quick_validate.py is performed using yaml.safe_load(), which is a secure practice for handling untrusted YAML input.

skill-creator