The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions found that attempt to override agent behavior, bypass safety filters, or extract system prompts.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or unauthorized network operations were detected. The components use standard React state for UI visibility.
[Obfuscation] (SAFE): No Base64, zero-width characters, homoglyphs, or encoded commands were identified in the code or documentation.
[Unverifiable Dependencies & Remote Code Execution] (SAFE): No remote script execution or unverifiable package installations are present. The skill references standard front-end libraries like framer-motion and lucide-react.
[Privilege Escalation] (SAFE): No commands involving sudo, system modification, or permission changes were found.
[Persistence Mechanisms] (SAFE): No attempts to create cron jobs, modify shell profiles, or establish startup persistence were detected.
[Metadata Poisoning] (SAFE): Metadata fields (name, description) are descriptive and free of hidden instructions or deceptive content.
[Indirect Prompt Injection] (SAFE): The skill does not ingest untrusted external data or provide a surface for third-party instruction injection.
[Dynamic Execution] (SAFE): No use of eval(), exec(), or runtime compilation of code was found. The logic is restricted to standard React component lifecycle and state management.

responsive-mobile-first