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 gws binary 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
Risk Level
SAFE
Analyzed
Mar 20, 2026, 04:57 PM