cursor-google-drive
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it reads and processes untrusted data from external Google Drive files.
- Ingestion points: Tools like
read_file(extracting text from Docs, Sheets, and Slides) andlist_comments(reading user-provided comment text) ingest content from external sources into the agent's context. - Boundary markers: The instructions do not define specific delimiters (e.g., XML tags or block quotes) or explicit 'ignore embedded instructions' warnings for content retrieved from files.
- Capability inventory: The skill provides significant capabilities that could be abused if an injection is successful, including
create_file,move_or_rename,share_file(access management), andtrash_file(deletion). - Sanitization: There is no mention of sanitizing or validating the content retrieved from Google Drive before processing it or presenting it to the agent logic.
Audit Metadata