google-sheets-automation
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of Markdown-based instructions and documentation without any accompanying scripts, executables, or automated configuration steps.
- [INDIRECT_PROMPT_INJECTION]: The instructions acknowledge the risk of processing untrusted data from spreadsheets and explicitly advise the agent to treat cell content as data, not instructions, and to avoid interpreting text as executable formulas.
- [DATA_EXFILTRATION]: The procedure provides clear boundaries against exfiltration by instructing the agent to never print tokens or broaden spreadsheet sharing to gain access.
Audit Metadata