gws-sheets

Pass

Audited by Gen Agent Trust Hub on May 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill functions as a wrapper for the 'gws' command-line utility, facilitating authorized Google Sheets operations. No malicious code, obfuscation, or suspicious network activities were identified within the instructions.
  • [SAFE]: The skill introduces a surface for indirect prompt injection as it retrieves content from spreadsheets that the agent then processes. This is an expected and necessary behavior for the skill's functionality.
  • [SAFE]: Data Ingestion Surface Analysis: 1. Ingestion points: Data retrieved from spreadsheets via 'gws sheets values' and 'gws sheets spreadsheets' (SKILL.md). 2. Boundary markers: None explicitly defined in the instructions. 3. Capability inventory: Command execution through the 'gws' binary (SKILL.md). 4. Sanitization: No explicit content sanitization is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
May 26, 2026, 10:52 AM
Security Audit — agent-trust-hub — gws-sheets