ClawRAG - Self-hosted RAG & Memory

• Analyzed: May 14, 2026, 3:38 AM
• Findings: 1
• Version: 1.2.0
• Hash: 2d1ece708adeda11a4c520626df7b17c00d9e3122125bfc9b7a1b8ef91733802
• Source: palm
• External report: View on VirusTotal

Findings (1)

The skill bundle is classified as suspicious due to its reliance on fetching and executing external code from various sources. The `SKILL.md` instructs the AI agent/user to perform `git clone` from a GitHub repository (github.com/2dogsandanerd/ClawRag.git), execute `docker compose up -d` which pulls and runs Docker images, and run `npx @clawrag/mcp-server` to install and execute an npm package. While these actions are plausibly needed for the stated purpose of setting up a local RAG service, they introduce a significant supply chain risk as the integrity of these external dependencies (GitHub repo, Docker images, npm package) cannot be guaranteed by the skill bundle itself. There is no clear evidence of intentional malicious behavior within the provided files, nor any prompt injection attempts to subvert the agent's core function.