connect-ai-googledrive

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where the agent ingests untrusted data from Google Drive files and possesses capabilities to modify the environment, creating a potential surface for indirect prompt injection.
  • Ingestion points: Untrusted data enters the agent context through the GetDocumentContent procedure (which returns Google Docs JSON) and the DownloadFile procedure (which returns file content as base64).
  • Boundary markers: There are no explicit instructions or delimiters provided in this skill to isolate the ingested file content from the agent's control logic.
  • Capability inventory: The skill grants access to powerful write operations, including UploadFile (creating/updating files), MoveResource (changing parent folders), UpdateResource (modifying metadata and content), and SQL UPDATE operations on the Files table.
  • Sanitization: The skill lacks instructions for sanitizing or validating the text content extracted from Google Docs or decoded from base64 files before the agent processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 02:09 PM
Security Audit — agent-trust-hub — connect-ai-googledrive