gws-drive
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
gws drivecommand to interact with various Google Drive API resources, including file manipulation and permission management. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Data enters the agent context through methods such as
files.get(metadata/content),files.download,comments.list, andreplies.list(SKILL.md). - Boundary markers: The file does not explicitly define boundary markers or delimiters for the ingested content, though it refers to shared security rules in a separate file.
- Capability inventory: The agent can list, read, create, and delete files, as well as modify shared drive permissions using the
gwsCLI (SKILL.md). - Sanitization: There is no evidence of content sanitization or validation for the data retrieved from the Drive API.
Audit Metadata