skills/marimo-team/marimo/marimo-pair/Gen Agent Trust Hub

marimo-pair

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a legitimate interface for managing marimo notebooks. It uses a private, internal API (marimo._code_mode) intended for agentic interaction with the marimo kernel. While it allows for command execution and file modification, these are the primary and intended purposes of the skill (enabling an agent to act as a notebook developer). All external references and documentation provided (e.g., anywidget, flechette) are to well-known, trusted developer tools and libraries. No evidence of prompt injection, data exfiltration, or obfuscation was found.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 10:39 PM
Security Audit — agent-trust-hub — marimo-pair