gws-sheets

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the gws command-line binary to interact with the Google Sheets API. It provides a structured way to execute shell commands for spreadsheet management.
  • [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection (Category 8) by ingesting data from external spreadsheets.
  • Ingestion points: Untrusted data enters the agent's context through methods like spreadsheets.get, values.get, and the +read helper command in SKILL.md.
  • Boundary markers: No specific boundary markers or instructions to treat spreadsheet content as data rather than instructions are present in this file.
  • Capability inventory: The skill possesses the capability to execute gws commands to write or update spreadsheet data, potentially allowing a chain where malicious data influences subsequent write actions.
  • Sanitization: The skill does not define any sanitization, validation, or filtering mechanisms for the data retrieved from the Google Sheets API.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 01:27 PM
Security Audit — agent-trust-hub — gws-sheets