skills/sethgammon/armory/live-preview/Gen Agent Trust Hub

live-preview

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands to capture screenshots using Playwright (e.g., npx playwright screenshot) and to start or interact with local development servers (e.g., npm run dev). These operations are typical for a visual verification tool and are restricted to the local development environment.
  • [EXTERNAL_DOWNLOADS]: The skill suggests installing the playwright package via npx or npm. Playwright is a widely used, well-known, and trusted browser automation library managed by Microsoft.
  • [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface as it ingests untrusted UI source code and rendered snapshots to automatically diagnose and fix rendering issues.
  • Ingestion points: Modified view-layer files (.tsx, .jsx, .vue, .svelte, .html, .css) and visual data from rendered local routes (SKILL.md).
  • Boundary markers: None identified.
  • Capability inventory: Shell command execution via npx and file system modification (Step 4: FIX).
  • Sanitization: The skill does not implement specific sanitization or validation of the ingested code or visual artifacts before processing them to generate fixes.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 07:07 AM