google-sheets-automation
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external spreadsheets via
get-textandget-rangecommands. This creates a vulnerability where malicious instructions embedded in spreadsheet cells could be interpreted as instructions by the agent. - Ingestion points: Data retrieved from
scripts/sheets.pycommands as described inSKILL.md. - Boundary markers: The skill instructions do not specify any delimiters or safety headers to separate data from instructions.
- Capability inventory: The skill allows for local shell execution of Python scripts and full read/write access to the Google Sheets API.
- Sanitization: No sanitization or validation of the ingested spreadsheet data is mentioned.
- [COMMAND_EXECUTION]: The skill relies on executing shell commands where user-provided content (like spreadsheet IDs, cell ranges, or cell values) is passed as CLI arguments. This presents a risk of command injection if the agent interpolates unsanitized user input into the
python scripts/sheets.py ...command strings.
Audit Metadata