recipe-generate-report-from-sheet
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Google Sheets, which creates a surface for indirect prompt injection if the spreadsheet content contains instructions designed to manipulate the agent's behavior.
- Ingestion points: The skill uses the
gws sheets +readcommand to import data from a user-providedSHEET_IDinSKILL.md. - Boundary markers: The instructions do not define boundary markers or include warnings for the agent to ignore instructions embedded within the spreadsheet data.
- Capability inventory: The skill utilizes
gws docs documents create,gws docs +write, andgws drive permissions createcommands, allowing it to generate files and share them externally based on the ingested data. - Sanitization: There is no evidence of input validation or sanitization applied to the spreadsheet data before it is written to a document or used in the workflow.
Audit Metadata