skills/sorrycc/skills/frontend-rails/Gen Agent Trust Hub

frontend-rails

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads the playwright package and its dependencies during setup to provide browser automation capabilities.
  • [COMMAND_EXECUTION]: Utility scripts such as compare.mjs and walk.mjs execute Node.js commands to run internal auditing logic via spawn and spawnSync.
  • [INDIRECT_PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection through its auditing and walkthrough features:
  • Ingestion points: gate/walk.mjs scrapes text and control labels from web pages, and gate/run.mjs captures screenshots for AI analysis.
  • Boundary markers: Subagent prompts in gate/walkthrough.md and gate/vision-questions.md do not include explicit instructions to disregard embedded malicious text within the audited page content.
  • Capability inventory: The subagent is empowered to interact with the browser (clicking, typing, selecting) based on the instructions it interprets from the page.
  • Sanitization: No sanitization is performed on the text extracted from the pages before being sent to the AI subagent.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 07:17 AM