ClawHub
Back to skill

Security audit

Llm Provider Ai Tool Free

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed API-integration guide for using an external LLM service, including chat, file upload, assistants, embeddings, and image generation.

Install only if you intend to let the agent call this external LLM API. Treat prompts, metadata, and uploaded files as data sent to the provider; avoid sensitive or regulated documents unless that use is approved, and use a scoped API key rather than a broadly privileged one.

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 (3)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger condition is overly broad ('whenever AI model invocation, intelligent chat, agent orchestration, or LLM application is needed'), which can cause the skill to be invoked for many unrelated requests. In an agent ecosystem, accidental invocation increases the chance of unintended external API use, data transmission, and tool execution without clear user intent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill advertises file upload and third-party API usage but does not clearly warn that user content may be transmitted to an external service. This creates privacy and compliance risk because users may provide sensitive documents without understanding that data leaves the local environment.

External Transmission

Medium
Category
Data Exfiltration
Content
-F "file=@./knowledge.pdf"

# 创建助手并绑定文件
curl -X POST "https://api.llm-provider.com/v1/assistants" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
Confidence
92% confidence
Finding
https://api.llm-provider.com/

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.