box-automation

Warn

Audited by Snyk on Feb 27, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md requires using BOX_SEARCH_FOR_CONTENT (full-text search across files, folders, and web links) and tools like BOX_GET_FILE_INFORMATION / BOX_DOWNLOAD_FILE to read file_content and web_link items stored in Box, which are user/third-party content that the agent will ingest and can materially influence subsequent tool use and decisions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The skill requires adding the MCP server https://rube.app/mcp and explicitly instructs calling RUBE_SEARCH_TOOLS at runtime to fetch tool schemas from that endpoint, meaning remote content from that URL directly controls the agent's available instructions and is a required runtime dependency.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 09:32 AM