gws-workflow

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified. The skill's behavior is consistent with its stated purpose of facilitating Google Workspace productivity workflows.
  • [COMMAND_EXECUTION]: The skill executes commands using the gws CLI tool, which is a required binary for interacting with Google Workspace services. This usage is expected for a CLI-based integration from this vendor.
  • [PROMPT_INJECTION]: The skill processes data from Google Workspace services (e.g., Gmail and Calendar), creating an indirect prompt injection surface. (1) Ingestion points: Content from emails and meetings enters the context via the gws workflow command flags. (2) Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the wrapper. (3) Capability inventory: The skill can read productivity data and perform actions via the gws binary. (4) Sanitization: Content is passed to the CLI tool parameters. This is an inherent risk of automated productivity tools but is managed by the trusted vendor's infrastructure.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 10:49 PM