ClawHub
Back to skill

Security audit

育儿号全平台内容产出引擎

Security checks across malware telemetry and agentic risk

Overview

This appears to be a parenting/content-generation skill whose noted risks are mainly overbroad activation, local file creation, and default persona choices rather than hidden or harmful behavior.

Install if you want a structured parenting/content creation assistant and are comfortable with it writing generated files. Before use, specify the target language, locale, platform, persona, and output folder, and review generated content before publishing anywhere.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The trigger phrases are numerous and generic enough that ordinary parenting or content-creation requests could unintentionally activate the skill. This can cause the agent to launch a complex workflow, including downstream Task invocations and file-writing behavior, without a clearly scoped user intent boundary.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to create multiple directories and files on disk, and even defines a default relative output path, but it does not require an explicit user confirmation or present a clear warning about filesystem side effects. In an agent environment with write capabilities, this can lead to unexpected file creation, overwrites, clutter, or writes to unintended relative locations.

Natural-Language Policy Violations

Medium
Confidence
87% confidence
Finding
The file hard-codes Chinese personas and platform-specific roles, and explicitly says they should be selected automatically without asking the user. This can cause unintended language/locale targeting, produce outputs misaligned with user expectations or compliance needs, and reduce user control over how content is generated. In this skill’s context, the risk is amplified because the skill is a multi-platform content generator and the persona choice directly shapes tone, platform strategy, and audience assumptions.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.