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 gws command-line utility to interact with the Google Docs API. It requires the gws binary to be installed on the system to perform operations such as batchUpdate, create, and get.- [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 get method 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 batchUpdate and create, 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
Risk Level
SAFE
Analyzed
Sep 19, 2026, 09:00 PM