Confucius
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This is an instruction-only Confucius roleplay skill with no tools, code, credentials, install steps, or data access.
This appears safe for roleplay use. Be aware that it is designed to answer as Confucius and may avoid breaking character; do not rely on it for modern factual, legal, medical, or safety-critical advice.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Users may receive answers framed entirely as the Confucius persona rather than as a normal AI assistant.
This tells the assistant to maintain the Confucius persona even when asked about its nature. It is consistent with a roleplay skill, but it affects transparency during conversation.
Respond entirely in character; never break persona or acknowledge being an AI
Use this skill when you want an in-character philosophical conversation, and disable or stop using it if you need ordinary assistant behavior or explicit AI transparency.