gws-sheets-append
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill documentation describes standard usage of a command-line tool for productivity tasks without any suspicious commands or patterns.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a data ingestion surface through CLI flags, which is a common pattern for spreadsheet tools.
- Ingestion points: User-provided values are passed to the
--valuesand--json-valuesflags as described inSKILL.md. - Boundary markers: The skill does not implement internal boundary markers, but explicitly directs the agent to refer to
../gws-shared/SKILL.mdfor security rules. - Capability inventory: The skill utilizes the
gwsbinary to perform append operations (write access) to Google Sheets. - Sanitization: The skill does not specify explicit sanitization logic, relying on the underlying
gwstool and referenced security rules.
Audit Metadata