The Agent Skills Directory

[SAFE]: The skill consists entirely of documentation, usage patterns, and configuration examples for the Google Gemini API. It contains no executable scripts or logic that would pose a security risk.
[EXTERNAL_DOWNLOADS]: The skill mentions using standard tools like curl to interact with official Google API endpoints (generativelanguage.googleapis.com). These are well-known, trusted services used for the skill's primary function.
[CREDENTIALS_UNSAFE]: The skill follows security best practices by advising the use of environment variables ($GOOGLE_API_KEY) for authentication rather than providing or requesting hardcoded secrets.
[PROMPT_INJECTION]: There are no instructions designed to bypass agent safety filters or override system behavior.

google-ai