chrome-extension-dev

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and process data from external web pages and browser console logs, which may contain untrusted content.
  • Ingestion points: mcp__claude-in-chrome__read_page and mcp__claude-in-chrome__read_console_messages in SKILL.md.
  • Capability inventory: Uses mcp__claude-in-chrome__javascript_tool to execute code in the page context and mcp__claude-in-chrome__computer for visual feedback.
  • Boundary markers: None identified in the skill documentation.
  • Sanitization: No sanitization or validation of the ingested browser data is performed.
  • [EXTERNAL_DOWNLOADS]: The skill documentation recommends the installation of the 'Extensions Reloader' utility from the Chrome Web Store, which is a well-known service.
  • [DYNAMIC_EXECUTION]: The skill utilizes the browser's JavaScript execution tool to interact with the extension under development. This is a core component of the intended functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 03:18 PM
Security Audit — agent-trust-hub — chrome-extension-dev