recipe-compare-sheet-tabs
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external Google Sheets, which serves as a vector for untrusted content ingestion.
- Ingestion points: The skill uses
gws sheets +readto fetch data from two spreadsheet ranges defined inSKILL.md. - Boundary markers: There are no delimiters or instructions provided to the agent to distinguish between the spreadsheet data and the skill's operational instructions.
- Capability inventory: The agent reads the external spreadsheet content and performs a comparison, which updates the agent's context with untrusted data.
- Sanitization: The skill lacks any mechanism to sanitize or validate the content retrieved from the Google Sheets before processing it.
Audit Metadata