design-mobile-first

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides automated auditing commands using cat, grep, rg (ripgrep), and ls to survey the project's existing mobile-responsive configuration. These commands are local, read-only, and serve to synchronize the agent with the project's current state.
  • [INDIRECT_PROMPT_INJECTION]: The skill involves reading project source code to identify mobile patterns. While this establishes a potential data ingestion point, the risk is negligible as the skill performs non-destructive UI design tasks and does not involve high-risk actions like network communication or credential access.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 07:53 PM