mayun-perspective

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates within a defined persona and does not request or use dangerous capabilities such as shell execution or network access. All operations are local and consistent with its stated purpose.
  • [EXTERNAL_DOWNLOADS]: The installation instructions utilize a command (npx skills add nuwa-skills/mayun-skill) pointing to the vendor's repository. This is a standard installation mechanism for this skill provider.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user input in the form of business scenarios to generate persona-based responses. While it lacks explicit separators for user content, the risk is negligible as the agent is restricted to text generation and reading local reference files such as research.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 10:09 AM
Security Audit — agent-trust-hub — mayun-perspective