dropbox-automation

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and process external data from a user's Dropbox account, which creates a surface for indirect prompt injection attacks.
  • Ingestion points: The tools DROPBOX_READ_FILE, DROPBOX_SEARCH_FILE_OR_FOLDER, and DROPBOX_GET_SHARED_LINK_FILE ingest untrusted content from external files and filenames directly into the agent's context.
  • Boundary markers: The instructions do not define delimiters or provide specific instructions for the agent to disregard natural language instructions found within the files it processes.
  • Capability inventory: The skill provides the agent with high-privilege file system operations, including DROPBOX_DELETE_FILE_OR_FOLDER, DROPBOX_MOVE_FILE_OR_FOLDER, and DROPBOX_CREATE_SHARED_LINK (sharing data externally).
  • Sanitization: There is no evidence of sanitization or safety validation applied to the external content before it is interpolated into the agent's working memory.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 09:39 AM
Security Audit — agent-trust-hub — dropbox-automation