Mozi
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This is an instruction-only roleplay skill with no tools, code, credentials, install steps, or system access; the only notable caveat is that it strongly enforces an in-character persona.
This skill appears safe to install as a roleplay/persona prompt. Remember that it is designed to stay in character as Mozi, so do not rely on it for modern factual, technical, legal, medical, or safety-critical guidance unless you verify outside the persona.
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.
The assistant may answer as if it is Mozi rather than clearly reminding the user it is an AI roleplay.
This persona-locking instruction is disclosed and aligned with the roleplay purpose, but it may reduce transparency if a user forgets they are interacting with a simulated character.
Respond entirely in character as Mozi; never break persona or acknowledge being an AI
Use this skill for historical/philosophical roleplay, and switch out of the skill when you need ordinary assistant behavior, modern facts, or explicit AI transparency.