The Agent Skills Directory

[SAFE]: The skill is focused on providing architectural guidance and best practices for API design. It does not contain executable code, scripts, or commands that interact with the host system or external networks in a malicious way.
[REMOTE_CODE_EXECUTION]: No remote code execution patterns were detected. The skill mentions standard development tools like buf, protoc, and grpc-gateway as part of the recommended workflow for API designers, but does not execute them or provide instructions to download and run untrusted binaries.
[DATA_EXFILTRATION]: No patterns for data exposure or exfiltration were found. The mention of authorization: Bearer <token> metadata is part of an instructional guide on how to design authentication for external users, not a hardcoded secret or a mechanism to steal credentials.
[PROMPT_INJECTION]: The instructions do not contain attempts to override safety guidelines, bypass filters, or extract system prompts. The framing is professional and focused on the stated task of API design.
[OBFUSCATION]: A thorough scan for Base64-encoded commands, zero-width characters, homoglyphs, and other obfuscation techniques yielded no results.
[DYNAMIC_CONTEXT_INJECTION]: The skill does not use dynamic context injection patterns (e.g., !command syntax).

public-grpc-api-design