ClawHub
Back to skill

Security audit

Relationship Nurture Assistant

Security checks across malware telemetry and agentic risk

Overview

This is a relationship-advice skill with coherent disclosed behavior and no evidence of hidden access, data collection, persistence, or destructive actions.

Before installing, note that this skill gives relationship communication suggestions in Chinese and is not professional therapy, legal, or crisis support. Users should review advice before applying it to sensitive personal situations, and the publisher should improve the manifest description and clarify language expectations.

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 (3)

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The README presents the skill entirely in Chinese and does not offer a language-selection mechanism or document that the skill is intentionally locale-specific. This can cause users or downstream agents to misunderstand the skill’s purpose or outputs, creating usability and safety issues when advice is consumed by users who cannot read the language.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger phrases are broad and overlap with many ordinary conversations about family, emotions, or conflict, which can cause the skill to activate outside the author's intended scope. In a relationship-advice skill, unintended activation can surface sensitive guidance in inappropriate contexts, increasing the risk of privacy issues, user confusion, or advice being applied to the wrong relationship type.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The manifest description is so generic ('auto-generated skeleton') that it does not meaningfully define the skill’s purpose or intended activation context. This increases the risk of accidental or overly broad invocation, making it harder for users or reviewers to understand when the skill should run and whether its behavior is appropriate.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.