gws-sheets-append

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill documents the use of the gws CLI tool for appending data to Google Sheets spreadsheets. The gws tool is a binary requirement defined in the skill metadata.
  • [INDIRECT_PROMPT_INJECTION]: The skill takes user-provided input through the --values and --json-values flags to be written to a spreadsheet. This presents a potential surface for indirect prompt injection if the resulting spreadsheet data is later consumed by an LLM without proper sanitization. Ingestion points: Data provided to --values and --json-values flags in SKILL.md. Boundary markers: None identified in this specific instruction file. Capability inventory: The skill performs write operations to Google Sheets via the gws command line tool. Sanitization: No explicit sanitization or validation of the input strings is described within this file.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 04:27 AM
Security Audit — agent-trust-hub — gws-sheets-append