evan-you-perspective

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is primarily composed of instructions and extensive technical research related to Evan You's design philosophy and decision-making history. It does not contain executable code, scripts, or dangerous commands.
  • [DATA_EXFILTRATION]: While the skill contains many external URLs in its research documentation, these point to reputable sources such as official blogs (vuejs.org, voidzero.dev), social media (Twitter/X), and well-known technology podcasts (Changelog, CoRecursive). No suspicious domains or exfiltration patterns were found.
  • [PROMPT_INJECTION]: The skill uses detailed role-play instructions to define a persona, but it does not attempt to bypass agent safety filters or override global system instructions. It includes an 'Honesty Boundary' section to explicitly define the limits of its capabilities.
  • [COMMAND_EXECUTION]: No shell commands or system-level operations are included in the skill files. The workflow suggests using standard agent tools like WebSearch for factual verification, which is a common and legitimate practice for persona-based skills.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 12:02 PM