marks-perspective

Pass

Audited by Gen Agent Trust Hub on Jul 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is composed entirely of Markdown files containing instructions and reference data. There are no executable scripts or command-line patterns.
  • [SAFE]: No obfuscation, prompt injection, or persistence mechanisms were found.
  • [SAFE]: No hardcoded credentials or sensitive data exposure patterns were detected.
  • [SAFE]: The skill uses local file references to its own internal documentation (e.g., references/research.md) which is a standard and safe behavior for retrieving context.
  • [SAFE]: All external links and resources point to the author's own repositories (nuwa-skills) or well-known platforms like GitHub and Claude AI, consistent with the provided vendor context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 26, 2026, 05:12 AM
Security Audit — agent-trust-hub — marks-perspective