ClawHub
Back to skill

Security audit

Self Love Confidence

Security checks across malware telemetry and agentic risk

Overview

This is a simple self-help prompt skill with no executable code, network access, credential use, persistence, or hidden behavior found.

Before installing, consider whether you are comfortable with a wellness-oriented skill activating from broad phrases during emotional conversations. I found no evidence that it runs code, sends data elsewhere, accesses credentials, or changes your system.

SkillSpector

By NVIDIA
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
92% confidence
Finding
The trigger phrases include broad, common language such as "affirmations," "feeling insecure," and "self worth," which can cause the skill to activate during ordinary conversation rather than from an intentional user request. In a mental-wellness context, unintended invocation is especially risky because it may capture or redirect sensitive emotional disclosures when the user did not mean to engage this skill.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.