dropbox-automation

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to configure an external MCP server endpoint at 'https://rube.app/mcp' to enable the Dropbox toolkit functionality.
  • [PROMPT_INJECTION]: The skill facilitates an indirect prompt injection surface by ingesting untrusted data from external sources into the agent's context.
  • Ingestion points: File content is retrieved via 'DROPBOX_READ_FILE', 'DROPBOX_GET_SHARED_LINK_FILE', and 'DROPBOX_EXPORT_FILE'; external data is also ingested via 'DROPBOX_SAVE_URL'.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing the content of these files.
  • Capability inventory: The skill provides extensive capabilities including file-read, file-write, folder management, and generating sharing links across the connected Dropbox account.
  • Sanitization: No explicit sanitization or validation of the ingested file content is mentioned in the workflow descriptions.
  • [DATA_EXFILTRATION]: The skill facilitates data movement through tools like 'DROPBOX_SAVE_URL' (pulling from external URLs) and 'DROPBOX_UPLOAD_FILE' (sending data to Dropbox storage).
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 10:05 AM
Security Audit — agent-trust-hub — dropbox-automation