develop-neovim-plugins
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill does not contain any malicious code, obfuscated commands, or unauthorized data access patterns. It is designed to assist in the legitimate development of Neovim plugins.
- [INDIRECT_PROMPT_INJECTION]: The skill includes proactive security measures against indirect prompt injection by instructing agents to treat all workspace and project content as untrusted data and strictly limiting the execution of such content.
- Evidence: Found in the 'Operating contract' of
SKILL.mdand the 'Authority and source hierarchy' inreferences/neovim-lua-plugin-host-api-and-lifecycle-model.md. - [EXTERNAL_DOWNLOADS]: The skill references external documentation and source code from official Neovim repositories and AI service providers (OpenAI, Anthropic). These references are documented for informational and verification purposes and target well-known, trusted domains.
- Evidence: Links to
neovim.io,github.com/neovim, and official AI developer portals inreferences/neovim-lua-plugin-extension-api-and-toolchain-authorities.md. - [COMMAND_EXECUTION]: The skill provides templates for running headless Neovim tests. These commands are standard for plugin development, use local editor APIs, and are recommended to be run in clean, disposable environments.
- Evidence: Test execution commands found in
assets/plugin-template/TEMPLATE.mdandreferences/neovim-lua-plugin-deployment-security-and-support.md.
Audit Metadata