recipe-compare-sheet-tabs
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads content from external spreadsheet tabs, creating a potential vector for indirect prompt injection if the sheet contains malicious content.
- Ingestion points: Data is pulled from spreadsheet ranges
January!A1:DandFebruary!A1:Dviagws sheets +readinSKILL.md. - Boundary markers: Absent.
- Capability inventory: The skill only instructs the agent to compare data and does not execute dangerous system commands or network operations.
- Sanitization: Absent.
Audit Metadata