ClawHub
Back to skill

Security audit

better-soul

Security checks for vulnerabilities and agentic risk

Overview

This is a simple writing-guidance skill for creating SOUL.md personality documents, with no code execution, persistence, credential access, or hidden data handling.

Before installing, consider that SOUL.md can shape an agent's personality and tone, so review generated SOUL.md content carefully before using it as a global or persistent agent behavior file. No executable or data-access behavior was found in the inspected artifact.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill description is broadly scoped to 'creating, revising, or improving SOUL.md' and can overlap with ordinary writing or editing requests, making it likely to trigger in contexts beyond narrowly intended use. Over-broad invocation increases the chance that untrusted skill instructions influence unrelated agent behavior or persona configuration, which is especially sensitive because SOUL.md shapes how an agent behaves globally.

Static analysis

No suspicious patterns detected.