gws-shared

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTIONNO_CODE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the official Google Workspace CLI repository on GitHub (github.com/googleworkspace/cli) for installation and support (SKILL.md).
  • [COMMAND_EXECUTION]: The skill provides extensive examples of shell commands for the gws CLI tool, which allows the agent to interact with Google Workspace services like Gmail, Drive, and Sheets (SKILL.md).
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from Google Workspace services like Gmail and Drive (SKILL.md), which represents an indirect prompt injection surface. Boundary markers are not explicitly defined in the instructions (SKILL.md). Capability inventory includes subprocess execution of the gws binary for Workspace operations (SKILL.md). Sanitization is addressed via documentation for the --sanitize flag to utilize Model Armor for content safety (SKILL.md).
  • [NO_CODE]: The skill does not bundle any executable scripts or binaries, relying instead on pre-installed system tools (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 04:57 PM