univer-workspace-cli

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the univer-workspace-cli package globally via npm from the official registry (registry.npmjs.org), which is a well-known and trusted service.
  • [COMMAND_EXECUTION]: The skill executes multiple shell commands using the univer-workspace-cli binary to configure the environment, authenticate users, and interact with remote workspaces.
  • [INDIRECT_PROMPT_INJECTION]: The skill operates on remote Workspace files (Sheets, Docs, Slides), which introduces an attack surface where untrusted data within these files could contain instructions intended to influence the agent's behavior.
  • Ingestion points: Remote Workspace files, Personal Spaces, and Team Spaces accessed via the CLI tool (SKILL.md).
  • Boundary markers: None identified in the provided instructions.
  • Capability inventory: The CLI is capable of staging files, committing mutations, inspection, and generating review URLs across various file types.
  • Sanitization: No evidence of explicit sanitization or filtering of remote file content before processing is provided in the discovery metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 01:33 AM
Security Audit — agent-trust-hub — univer-workspace-cli