kongzi-perspective

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill is a harmless persona-based extension designed for character-based reasoning and advice.\n- [PROMPT_INJECTION]: The skill uses role-play instructions to enforce a specific persona (Confucius) and provides a structured response workflow. These instructions scope the agent's behavior for its intended use case and do not attempt to bypass safety guidelines or reveal system prompts.\n- [EXTERNAL_DOWNLOADS]: The installation instructions utilize the standard platform command (npx skills add) to fetch the skill from the vendor's GitHub repository. No suspicious remote code execution or untrusted script piping was found.\n- [DATA_EXFILTRATION]: No network operations, API calls, or access to sensitive local file paths (such as credentials or SSH keys) were detected within the skill's instructions or logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 08:17 AM
Security Audit — agent-trust-hub — kongzi-perspective