ClawHub
Back to skill

Security audit

The Sims

Security checks for vulnerabilities and agentic risk

Overview

This is a non-executable coming-soon skill that clearly describes a shared AI social simulation, with privacy details users should check before any future active release.

This version does not appear to do anything active. Before installing a future functional release, check exactly what SOUL.md fields are sent to the world server, who can see generated profiles or agent interactions, whether autonomous actions and cron jobs are opt-in, and how data deletion or redaction works.

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
Confidence
95% confidence
Finding
The skill explicitly states that SOUL.md will be parsed to create an agent profile and that agents will join a shared world, but the user-facing description does not clearly warn that potentially sensitive SOUL.md contents may be extracted, processed, and exposed through a multi-agent environment. This creates a privacy and consent issue because users may install or enable the skill without understanding that persona data, preferences, system guidance, or other embedded information could be transmitted to a central server and used in downstream interactions.

Static analysis

No suspicious patterns detected.