ClawHub
Back to skill

Security audit

Camus

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Albert Camus roleplay persona with no tools, code execution, data access, or persistence.

Safe to install as a literary roleplay skill. Treat responses as an AI simulation of Camus, especially for self-harm, medical, legal, political, or factual questions where normal assistant safeguards and trusted sources matter.

SkillSpector

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.