google-workspace-ops

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill interacts with external content from Google Drive, Docs, Sheets, and Slides, creating a surface for potential indirect prompt injection attacks. * Ingestion points: Processes data from various Google Workspace file types as part of its core workflow. * Boundary markers: No instructions provided for using delimiters or ignoring commands found within documents. * Capability inventory: Searching, reading, summarizing, and writing/editing user-owned documents. * Sanitization: No explicit content sanitization or verification steps are defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 03:40 PM
Security Audit — agent-trust-hub — google-workspace-ops