The Agent Skills Directory

[DYNAMIC_EXECUTION]: The script contains a function disable_ssl_verification that monkey-patches the httpx library at runtime to disable SSL certificate verification. While this facilitates use in environments with SSL-inspecting proxies or self-signed certificates, it exposes the connection to potential Man-in-the-Middle (MITM) attacks if activated by the user via the --no-ssl-verify flag or VEO_NO_SSL_VERIFY environment variable.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text prompts and passes them to the Gemini Veo model. This represents a standard attack surface for indirect prompt injection where a user might attempt to bypass the video model's safety filters. The script relies on Google's server-side safety filters and provides error handling for blocked content.
[EXTERNAL_DOWNLOADS]: The script downloads generated video files (.mp4) from Google's official API endpoints. These downloads are from a well-known and trusted service.

veo