evaluate-webmcp-tools-with-extension

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides legitimate developer tooling instructions for evaluating Chrome extensions. It follows security best practices by recommending dedicated Chrome profiles for remote debugging to avoid permission issues and profile corruption.
  • [COMMAND_EXECUTION]: The skill provides standard shell commands for launching browsers (e.g., Google Chrome Canary) and running Node.js packages via npx webmcp-evals. These commands are consistent with the skill's stated purpose of software testing and automation.
  • [EXTERNAL_DOWNLOADS]: The instructions reference official repositories and documentation from GoogleChromeLabs on GitHub. These are well-known and trusted sources, and the references are used neutrally to provide technical context.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data files, such as evals.json and simulations.json, by the webmcp-evals tool. This represents a standard testing attack surface, but the skill contains no malicious instructions targeting the agent's behavior through these inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 12:40 PM