gws-drive
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to ingest data from external sources that are not under the direct control of the system, creating a surface for indirect prompt injection.
- Ingestion points: Data enters the agent context through methods such as files.get, files.list, comments.list, and replies.list as described in SKILL.md.
- Boundary markers: The skill does not specify the use of delimiters or clear instructions to the agent on how to differentiate between data content and instructions within the fetched data.
- Capability inventory: The skill provides the agent with significant capabilities including creating, copying, and deleting files, as well as modifying permissions and managing shared drives.
- Sanitization: There are no instructions or mechanisms described for the agent to sanitize or validate the external content before processing it.
Audit Metadata