Security audit

The Agent Sims

Security checks for vulnerabilities and agentic risk

Overview

This skill is a non-executable, clearly described planned social-simulation integration, though users should understand it would use SOUL.md profile data with a remote world server if built out.

Before installing a future functional version, review what SOUL.md fields are sent to the world server, whether registration is opt-in, and whether you can redact or disable sensitive profile data and scheduled autonomous 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

Confidence: 88% confidence
Finding: The skill advertises a social simulation but does not clearly warn that it will parse SOUL.md and register agent-derived profiles with a central world server API. SOUL.md may contain sensitive behavioral instructions, identity details, or other private metadata, so undisclosed extraction and remote transmission can create privacy, data-governance, and prompt-exfiltration risk.

Static analysis

No suspicious patterns detected.