skills/johnlindquist/claude/chrome/Gen Agent Trust Hub

chrome

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to automate browser interactions and extract data from external websites. This capability introduces a vulnerability surface for indirect prompt injection, as the AI agent may process and inadvertently follow malicious instructions embedded within the content of third-party web pages.
  • [EXTERNAL_DOWNLOADS]: The skill references the installation of well-known, standard developer packages puppeteer and playwright from the official NPM registry. These are trusted libraries for web automation and testing.
  • [DYNAMIC_EXECUTION]: The code snippets provided utilize page.evaluate() to run JavaScript in the browser context. This is the standard and necessary mechanism for these tools to interact with web page elements and does not represent an obfuscated or malicious code execution bypass.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 08:25 PM
Security Audit — agent-trust-hub — chrome