gdocs
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- COMMAND_EXECUTION (LOW): The skill relies on the 'gog' CLI tool (v0.10.0) to perform operations on Google Docs via subprocess execution. While this is the intended functionality, it grants the agent significant control over the user's Google Workspace environment.- PROMPT_INJECTION (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8).
- Ingestion points: The
gog docs catcommand reads the full content of Google Documents into the agent's context. - Boundary markers: Absent. The skill does not provide instructions to wrap document content in delimiters (e.g., XML tags) or warn the agent to ignore embedded instructions.
- Capability inventory: The agent has capabilities to create, modify, delete, and export documents using the
gogtool. - Sanitization: No sanitization, escaping, or validation is performed on the content retrieved from documents before it is processed by the agent.
Audit Metadata