gws-sheets-read
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data from Google Sheets, creating a surface for instructions embedded in spreadsheets to influence agent behavior.
- Ingestion points: The output of the
gws sheets +readcommand (SKILL.md). - Boundary markers: None specified in the documentation to delimit external data or warn the agent against following embedded instructions.
- Capability inventory: While this specific skill is described as read-only, the agent's overall capability set (provided by other skills) determines the potential impact of an injection.
- Sanitization: There is no evidence of sanitization, filtering, or validation performed on the retrieved spreadsheet values before they enter the prompt context.
Audit Metadata