gws-docs-write
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
gwsCLI tool to interact with Google Docs. This is a standard and intended behavior for this skill's functionality. - [INDIRECT_PROMPT_INJECTION]: The skill accepts arbitrary text via the
--textflag and writes it to a document, creating a potential surface for indirect prompt injection if the source data is attacker-controlled. - Ingestion points: The
--text <TEXT>parameter inSKILL.mdallows external data into the document environment. - Boundary markers: The skill instructions do not specify any delimiters or safety markers to differentiate between intended text and potential instructions within the input.
- Capability inventory: The skill has write capabilities to modify Google Documents via the
gwsCLI tool. - Sanitization: There is no evidence of sanitization, filtering, or validation of the input text within the skill instructions.
Audit Metadata