The Agent Skills Directory

[SAFE]: The skill acts as a comprehensive technical guide for Marko 6 development. It focuses on framework-specific syntax, reactivity models, and architectural patterns.
[DATA_EXFILTRATION]: No exfiltration patterns were detected. The skill includes proper security warnings, specifically advising against serializing sensitive data/secrets into the client-side $global.serializedGlobals object.
[PROMPT_INJECTION]: No attempts to override agent behavior, bypass safety filters, or extract system prompts were found. The instructions are purely instructional and focused on code quality.
[REMOTE_CODE_EXECUTION]: The skill does not contain any remote script downloads (e.g., curl|bash) or suspicious package installations. All mentioned dependencies (e.g., marko-run, @marko/vite, @marko/type-check) are standard tools within the official MarkoJS ecosystem.
[OBFUSCATION]: Comprehensive scanning for Base64 encoding, zero-width characters, homoglyphs, and other obfuscation techniques yielded no findings. The text and code samples are clear and verifiable.

marko6