dropbox-automation

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill creates an attack surface for indirect prompt injection through data ingestion.
  • Ingestion points: The tools DROPBOX_READ_FILE and DROPBOX_SEARCH_FILE_OR_FOLDER allow the agent to ingest content from arbitrary files and search results stored on Dropbox.
  • Boundary markers: The skill instructions do not provide delimiters or specific system instructions to treat content from these files as untrusted or to ignore embedded commands.
  • Capability inventory: The skill provides powerful file system and sharing capabilities, including DROPBOX_UPLOAD_FILE, DROPBOX_DELETE_FILE_OR_FOLDER, DROPBOX_MOVE_FILE_OR_FOLDER, DROPBOX_CREATE_SHARED_LINK, and DROPBOX_SAVE_URL, which could be abused if the agent follows malicious instructions embedded in a read file.
  • Sanitization: No sanitization or validation logic is described for the content retrieved from Dropbox before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external MCP server endpoint at https://rube.app/mcp as part of the setup process.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 07:56 AM