The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes Python scripts (scripts/security_scan.py, scripts/package_skill.py) that use subprocess.run to execute external tools like gitleaks and manage file packaging. These operations are restricted to the toolkit's intended development and security auditing workflows.
[EXTERNAL_DOWNLOADS]: The documentation provides instructions for downloading gitleaks from its official GitHub repository, which is a trusted and well-known service.
[DATA_EXFILTRATION]: No exfiltration patterns were detected. The skill is designed to improve data privacy through its security_scan.py script and sanitization_checklist.md, which help users identify and remove sensitive information.
[PROMPT_INJECTION]: The skill facilitates the generation of new skills, which introduces a surface for processing untrusted content. Ingestion points: SKILL.md creation and editing. Boundary markers: Not explicitly defined in templates. Capability inventory: subprocess.run calls in the scanning utility. Sanitization: The skill provides a mandatory security scanner and a comprehensive sanitization checklist to mitigate risks. No malicious intent was observed.
[SAFE]: No obfuscation, persistence mechanisms, or unauthorized privilege escalation attempts were found in the skill's code or instructions.

skill-creator