The Agent Skills Directory

[SAFE]: The skill consists solely of a documentation file (SKILL.md) that specifies an API interface. No executable scripts, binaries, or automated installation procedures are included, significantly reducing the local execution risk surface.
[DATA_EXPOSURE]: The skill correctly instructs the use of environment variables ($VENICE_API_KEY) for handling authentication tokens, adhering to security best practices for credential management.
[INDIRECT_PROMPT_INJECTION]: The skill identifies ingestion points for untrusted data through documented features like enable_web_search and enable_web_scraping. While these features allow external content to enter the agent's context, they are intended functionalities of the API and are documented as such.
[EXTERNAL_DOWNLOADS]: The skill references the official api.venice.ai domain for network requests. This is consistent with the skill's purpose and targets a well-known service associated with the API provider.

venice-chat