vibe-knowledge

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads its source code, templates, and assets from the official renoise-ai GitHub repository (renoise-ai/renoise-skills). This is a bootstrapping mechanism used to ensure the agent uses a version of the skill that has passed continuous integration.
  • [COMMAND_EXECUTION]: The skill utilizes shell commands such as curl, tar, and mkdir to fetch and organize its assets within the ~/.cache/renoise-skills/ directory.
  • [DYNAMIC_EXECUTION]: The skill dynamically loads its primary logic by downloading a specific commit archive of itself and instructing the agent to follow the instructions found within the downloaded SKILL.md file.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data (knowledge points and sourced facts) to generate video scripts. While this creates a data ingestion surface, it is consistent with the skill's primary purpose of video production.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 07:50 AM