ClawHub
Back to skill

Security audit

tantan-10agents

Security checks across malware telemetry and agentic risk

Overview

This is a Chinese market-intelligence prompt skill with broad activation wording, but no evidence of hidden access, persistence, code execution, or data exfiltration.

Install this if you want a Chinese-language market research assistant that may activate for many market, competitor, trend, and report-related prompts. Consider asking the publisher to narrow the trigger wording and make language behavior adaptive, but the reviewed artifact does not show malicious or hidden behavior.

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 (2)

Vague Triggers

High
Confidence
97% confidence
Finding
The skill is configured to trigger on extremely broad conditions such as any request to '了解外部市场情况' and includes a wide set of common business keywords. This can cause frequent unintended activation, routing ordinary conversation into this skill when the user did not explicitly request it, which creates instruction-collision risk, poor task selection, and expanded attack surface for prompt injection via skill invocation.

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The skill metadata and content enforce Chinese-language behavior and present only a Chinese persona/opening without offering user language choice or documenting a legitimate locale-only constraint. This can override user preference, reduce transparency, and increase the chance of unsafe or incorrect handling when the surrounding system or user is operating in another language.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal