dropbox-automation

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies a data ingestion surface by reading and searching file content from Dropbox using DROPBOX_READ_FILE and DROPBOX_SEARCH_FILE_OR_FOLDER. This could expose the agent to malicious instructions embedded in external documents. The skill does not specify the use of boundary markers or sanitization protocols to isolate this untrusted data. Given the skill's capabilities to delete files and perform batch operations, an injection could lead to unintended data loss or unauthorized modifications.
  • [EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external Model Context Protocol (MCP) server at https://rube.app/mcp and refers to toolkit documentation at composio.dev. These resources are infrastructure components necessary for the skill's functionality.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a wide variety of storage management commands, including creating, moving, and deleting files and folders based on user requests and agent logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 09:49 PM