ClawHub
Back to skill

Security audit

lxd-report

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only Chinese report-analysis skill with no tool use, persistence, or hidden data access.

Install this if you want a Chinese-language assistant for diagnosing work reports. Be mindful that it may activate when you paste obvious report drafts, including workplace-sensitive drafts, and that its template is designed for Chinese output.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

High
Confidence
95% confidence
Finding
The activation criteria are overly broad: the skill should be used not only on explicit analysis requests, but also whenever content merely appears to be a report draft. This can cause the agent to invoke the skill on ordinary feedback or editing requests without clear user intent, leading to inappropriate interception, misrouting, and possible unnecessary processing of sensitive workplace content.

Natural-Language Policy Violations

Medium
Confidence
87% confidence
Finding
Forcing output to always be in Chinese can override the user's language preference and increase the chance of misunderstanding, especially if the surrounding session is in another language. In mixed-language or international environments, this can degrade the reliability of the agent's response and potentially cause incorrect handling of business-sensitive content due to comprehension errors.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.