sense-setup

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for installing the sensemaking CLI tool globally using NPM (npm install -g sensemaking). This is a standard installation procedure for Node.js-based developer tools.
  • [EXTERNAL_DOWNLOADS]: The configuration involves downloading embedding models from Hugging Face (e.g., minishlab/potion-retrieval-32M) and database drivers from NPM (@duckdb/node-api, @tursodatabase/database). These downloads originate from well-known repositories and package registries.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to set up a knowledge retrieval system that processes markdown files. While this creates a potential surface for indirect prompt injection if the indexed content contains malicious instructions, this is an inherent property of retrieval-augmented generation (RAG) systems and the skill itself does not introduce specific vulnerabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 06:08 PM
Security Audit — agent-trust-hub — sense-setup