gws-docs
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to execute the
gwscommand-line utility to interact with the Google Docs API. It requires thegwsbinary to be installed on the system to perform operations such asbatchUpdate,create, andget.- [INDIRECT_PROMPT_INJECTION]: The skill provides an attack surface for indirect prompt injection by retrieving and acting upon content from external sources. - Ingestion points: The
gws docs getmethod fetches the latest version of a specified document, bringing potentially untrusted content into the agent's context. - Boundary markers: The skill lacks explicit instructions or delimiters to isolate document content or warn the agent to ignore instructions embedded within the text.
- Capability inventory: The skill includes powerful modification capabilities, specifically
batchUpdateandcreate, which allow the agent to edit or generate documents based on potentially poisoned input. - Sanitization: There is no evidence of content sanitization, filtering, or validation before the retrieved document data is used by the agent.
Audit Metadata