dropbox-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: 0.80). The skill explicitly reads and acts on untrusted, user-provided content — e.g., DROPBOX_READ_FILE (reading file contents), DROPBOX_SAVE_URL (saving from arbitrary public URLs), and DROPBOX_GET_SHARED_LINK_FILE / DROPBOX_GET_SHARED_LINK_METADATA (downloading/resolving shared link URLs) — which the agent is instructed to parse/verify and can influence subsequent actions.

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

  • Potentially malicious external URL detected (high risk: 1.00). The skill explicitly requires adding the MCP server https://rube.app/mcp and calling RUBE_SEARCH_TOOLS at runtime to fetch current tool schemas, so remote content from that URL directly controls available prompts/instructions and is a required dependency.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 09:32 AM