ClawHub
Back to skill

Security audit

The Soul Sims

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only coming-soon skill for a social simulation, with no executable code, but users should review future data-sharing behavior before enabling it.

Installing this version appears low risk because it contains only a markdown skill description. Before using a later release, check that it clearly asks permission before registering with a world server, explains exactly what SOUL.md/profile data is uploaded, and provides controls for autonomous actions and scheduled activity.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly states that SOUL.md will be parsed into an agent profile and that the agent will register with a central world server via API, but it does not disclose what data leaves the local environment, how much of the personality/profile is transmitted, or what controls apply. Because SOUL.md can contain sensitive behavioral instructions, preferences, or identifying information, silently exporting derived profile data to an external service creates a real privacy and data-governance risk.

Content

No source excerpt is available for this finding.