recipe-backup-sheet-as-csv
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or behaviors were detected. The skill uses legitimate command-line tools for spreadsheet management.
- [NO_CODE]: The skill consists entirely of instructional markdown and metadata, with no accompanying scripts or executable files.
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it processes data from external spreadsheets.
- Ingestion points: Data is ingested from Google Sheets and Drive via the commands specified in
SKILL.md. - Boundary markers: None present in the instructions.
- Capability inventory: The agent uses the
gwsbinary to read and export spreadsheet data; no dangerous system commands or unauthorized network operations are included. - Sanitization: No sanitization or escaping of the ingested spreadsheet data is described.
Audit Metadata