ClawHub
Back to skill

Security audit

Soul Question

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed reflection skill that analyzes text the user provides and shows no evidence of hidden data collection, external calls, persistence, or destructive behavior.

Install only if you are comfortable having your assistant analyze the text you paste. Redact secrets, credentials, regulated personal data, confidential business information, and private third-party communications unless you have permission to use them.

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
84% confidence
Finding
The trigger phrases include common language such as 'deep question' and 'challenge my thinking,' which can cause the skill to activate in ordinary conversations where the user did not intend to invoke this behavior. Unintended activation can lead to inappropriate processing of sensitive personal, workplace, or journal-like content and produce intrusive outputs in contexts where a different assistant behavior was expected.

Static analysis

No suspicious patterns detected.