Security audit
Rousseau
Security checks for vulnerabilities and agentic risk
Overview
This is a simple Rousseau roleplay skill with no tools, code execution, credentials, persistence, or hidden data access.
Safe to install as a roleplay/persona skill. Remember that it intentionally answers as Rousseau and may refuse modern framing, so do not rely on it for current facts, professional advice, or neutral historical analysis.
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.