p5js-hermes
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches its core components from the official NousResearch repository on GitHub. This is a well-known organization in the AI research community, and the download uses standard git sparse-cloning techniques to minimize data transfer.
- [COMMAND_EXECUTION]: Transparently documents shell commands required for installation, such as
git cloneandnpx skills add. These commands are standard for skill management and installation, with clear justifications provided for their use. - [INDIRECT_PROMPT_INJECTION]: As a tool for generating creative code, the skill inherently processes user descriptions. While this is a theoretical surface for instruction injection, the specialized focus on generative art and the lack of sensitive data access significantly limits the risk.
- [SAFE]: The skill's primary purpose is creative coding, and all external references trace back to legitimate infrastructure associated with the upstream project.
Audit Metadata