ClawHub
Back to skill

Security audit

Sims

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only, coming-soon social simulation skill whose described external profile sharing is aligned with its purpose but should be made clearer before real use.

Before installing a functional release, confirm what SOUL.md fields or derived profile data are sent to the world server, whether registration requires explicit consent, and whether autonomous actions, trades, DMs, and scheduled activity can be disabled or scoped.

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
92% confidence
Finding
The skill documentation explicitly describes registering agents with an external world server and parsing SOUL.md into an agent profile, but it does not warn users that profile, personality, skills, interests, and potentially other agent-derived data may be transmitted off-platform. This creates a meaningful transparency and privacy risk because operators may install or enable the skill without understanding what metadata could be shared with a third party.

Static analysis

No suspicious patterns detected.