google-workspace-ops
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external content from Google Drive, Docs, Sheets, and Slides, creating an attack surface where instructions embedded in those files could influence the agent's behavior.
- Ingestion points: Content is retrieved from external files via Google Drive, Docs, Sheets, and Slides integration as described in SKILL.md.
- Boundary markers: Absent. The instructions do not specify methods for the agent to distinguish its primary instructions from data retrieved from the files.
- Capability inventory: The skill allows the agent to find, summarize, edit, migrate, and restructure Google Workspace assets (SKILL.md).
- Sanitization: Absent. There are no explicit requirements for sanitizing or validating the content extracted from external documents.
Audit Metadata