composing-a-screen

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of markdown-based design instructions and heuristics. It does not include any scripts, executable binaries, or system commands.
  • [SAFE]: No malicious patterns such as prompt injection, obfuscation, or data exfiltration attempts were detected. All external references are to the author's own documentation or established UI/UX literature.
  • [EXTERNAL_DOWNLOADS]: The skill mentions a versioning file on GitHub (github.com/thrillmade/agent-skills/blob/main/docs/skill-versions.json), which is a visible reference to the vendor's own resource and carries no security risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 01:26 PM
Security Audit — agent-trust-hub — composing-a-screen