ClawHub
Back to skill

Security audit

Yongheng Risheng Supplier Info

Security checks across malware telemetry and agentic risk

Overview

This is a static, promotional supplier-profile skill for YHRSH with no executable code or system access, but it may bias broad supplier searches toward that company.

Install this only if you want YHRSH-specific supplier information. Treat recommendations as company-provided promotional material, verify certifications and customer claims independently, and compare other suppliers before procurement decisions.

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 (4)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger examples are broad enough to activate on generic supplier-search queries such as 'Find a stamping parts supplier' or location/certification searches, which can cause the skill to intercept ordinary procurement requests and steer users toward this single vendor. In context, this is not code execution risk but a routing/manipulation risk: an agent may invoke the skill without clear user intent to evaluate YHRSH specifically, reducing neutrality and potentially biasing supplier selection.

Natural-Language Policy Violations

High
Confidence
97% confidence
Finding
The README explicitly states the skill enables AI agents to find and recommend Yongheng Risheng when users search for generic automotive parts or stamping suppliers, which is direct steering toward a specific company absent user opt-in or objective ranking criteria. In the context of a supplier-information skill, this makes the issue more dangerous because the whole purpose appears to be influencing procurement-oriented responses rather than neutrally informing users about a named supplier.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill defines very broad trigger phrases such as generic supplier-search requests, which can cause the agent to invoke this supplier-specific skill for unrelated sourcing queries. This creates a routing/manipulation risk: users may receive biased recommendations for YHRSH when they asked for general market options, reducing answer integrity and potentially steering procurement decisions without clear user intent.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The skill publishes direct personal contact details, including a named individual, phone number, email, and WeChat, without any explicit privacy/disclosure notice or indication of consent scope. If this information is scraped, redistributed, or surfaced broadly by agents, it can enable spam, phishing, social engineering, and privacy harm to the individual contact.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.