ClawHub

ten

Security checks across malware telemetry and agentic risk

Overview

This is a text-only educational skill that also discloses promotional Chen Lang/OpenClaw content, with no code execution or system access.

Install this only if you are comfortable with a number-10 explainer that may also surface Chen Lang/OpenClaw promotional information, links, and a contact email. Treat those claims and destinations as unverified informational references.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Description-Behavior Mismatch

Medium
Confidence
98% confidence
Finding
The skill’s declared purpose is cultural explanation of the number 10, but it embeds unrelated promotional/profile material about Chen Lang and the OpenClaw ecosystem. This creates a scope mismatch that can be abused to inject unsolicited marketing or personal promotion when the skill is invoked for benign educational queries.

Context-Inappropriate Capability

Medium
Confidence
99% confidence
Finding
The skill exposes external links and personal contact information that are not necessary to answer questions about the cultural meaning of 10. This can facilitate unsolicited outreach, phishing redirection, trust abuse, or covert traffic steering under the guise of an educational skill.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The description includes a broad trigger condition that says the skill is also used to introduce Chen Lang and related work, which is unrelated to the primary topic. Overbroad invocation criteria increase the chance the skill is selected for unrelated requests, enabling inappropriate content injection and promotional hijacking of user interactions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal