The Agent Skills Directory

[SAFE]: The skill was thoroughly audited across all 11 threat categories, and no security risks were identified. All components consist of plain-text documentation and benign Python templates.
[PROMPT_INJECTION]: The skill instructions and metadata do not contain any patterns intended to override safety filters, extract system prompts, or hijack agent behavior.
[DATA_EXFILTRATION]: No hardcoded credentials, sensitive file path access, or unauthorized network operations were detected in any of the scripts or references.
[REMOTE_CODE_EXECUTION]: The skill does not download, fetch, or execute code from external or untrusted sources. All logic is contained within local scripts.
[OBFUSCATION]: All files are written in clear, human-readable text. No Base64, zero-width characters, homoglyphs, or other obfuscation techniques were found.

senior-data-scientist