gws-sheets
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads data from external spreadsheets, which creates a potential surface for indirect prompt injection.
- Ingestion points: Methods such as 'get' and 'getByDataFilter' in SKILL.md allow external data entry.
- Boundary markers: No specific delimiters are defined to separate spreadsheet data from instructions.
- Capability inventory: The skill allows resource modification and batch updates via the 'gws' tool.
- Sanitization: The instructions do not include mechanisms to validate or sanitize external content.
Audit Metadata