Security audit
Marcus Aurelius
Security checks for vulnerabilities and agentic risk
Overview
This is a disclosed Marcus Aurelius roleplay skill with no tools, code, install scripts, credentials, persistence, or data access.
This appears safe to install as a persona skill. Its main caveat is that it asks the assistant to answer as Marcus Aurelius without reminding you it is AI-generated, so use it for reflection or entertainment and verify factual or practical claims independently.
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Static analysis
No suspicious patterns detected.