The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified during the analysis.
[PROMPT_INJECTION]: The skill's instructions focus entirely on architectural best practices and do not contain any patterns intended to bypass safety guidelines or override agent behavior.
[DATA_EXFILTRATION]: No sensitive file paths, hardcoded credentials, or unauthorized network operations were detected.
[REMOTE_CODE_EXECUTION]: The skill mentions official tools like steiger and eslint-plugin-effector, which are standard for the described development workflow. No suspicious remote script execution (e.g., curl|bash) is present.
[DYNAMIC_EXECUTION]: The templates provided are static code examples for React, Effector, and TypeScript. No unsafe use of eval(), exec(), or dynamic code generation was found.
[OBFUSCATION]: All content is in plain text. No Base64, zero-width characters, or homoglyph-based obfuscation techniques were identified.

effector-fsd