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
GetDocumentContentprocedure (which returns Google Docs JSON) and theDownloadFileprocedure (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 SQLUPDATEoperations on theFilestable. - 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