ai-design-fix

Pass

Audited by Gen Agent Trust Hub on Nov 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads and executes the @enmera/ai-design-check package from the NPM registry using npx. This utility is a vendor-owned resource used to automate design audits and code fixes.
  • [COMMAND_EXECUTION]: The agent is instructed to run shell commands for auditing local files, scanning external URLs, and generating video reports using system utilities like Chrome and ffmpeg.
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted UI code and scans external URLs, which serves as a potential vector for indirect prompt injection. To mitigate this, the instructions explicitly command the agent to treat all analyzed content as data rather than instructions and to refuse any behavioral overrides found within the files.
  • [DATA_EXFILTRATION]: Through the scan command, the skill makes network requests to arbitrary URLs to perform design and accessibility checks. This network activity is part of the intended functionality but represents a network ingestion surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 8, 2026, 02:38 AM