skills/vercel-labs/emulate/google/Gen Agent Trust Hub

google

Pass

Audited by Gen Agent Trust Hub on Oct 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • Remote Package Invocation: The skill utilizes npx to execute the emulate tool from the npm registry. This pattern involves fetching and running code at runtime, which is a common practice for development utilities but introduces an external dependency.
  • Local Command Execution: The skill employs Bash to run emulator commands and curl to simulate API requests. These operations are scoped to local listeners (defaulting to 127.0.0.1) to facilitate testing without connecting to live Google services.
  • Mock Credential Management: Examples in the documentation include mock OAuth client_secret and user data for seeding the emulator. These values are used for local configuration and are not real production secrets.
  • Indirect Prompt Injection Surface: The skill allows seeding the emulator with mock data (e.g., email bodies in messages, file contents in drive_items) within SKILL.md. This data enters the agent's context during testing. While the emulator facilitates local development, the absence of explicit boundary markers or sanitization in the mock data examples means that any instructional text embedded in these fields could potentially influence an agent processing the emulator's output.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 16, 2026, 06:34 AM