box-automation

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires configuring a remote MCP server at https://rube.app/mcp, which serves as the provider for all operational tools.
  • [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by processing data from Box (file contents, names, and metadata) which is untrusted external input.
  • Ingestion points: Untrusted data enters the context via BOX_SEARCH_FOR_CONTENT (searching file content) and BOX_LIST_ITEMS_IN_FOLDER (listing folder contents).
  • Boundary markers: There are no boundary markers or instructions to isolate or ignore instructions embedded in the processed data.
  • Capability inventory: The skill possesses powerful capabilities including BOX_UPLOAD_FILE, BOX_DELETE_FOLDER, BOX_UPDATE_FILE, and BOX_CANCEL_BOX_SIGN_REQUEST.
  • Sanitization: No sanitization or validation of the retrieved content is mentioned in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 06:56 AM