ClawHub
Back to skill

Security audit

Jike Hot Cn

Security checks across malware telemetry and agentic risk

Overview

This skill is low risk because it only prints built-in sample Jike-style posts and does not access accounts, files, credentials, or the network.

This appears safe to install from a security standpoint, but it does not provide real-time Jike content. Expect sample/mock output only, and be aware that the broad Chinese trigger "圈子" may activate the skill in some unrelated community-discussion prompts.

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 (2)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The term "圈子" is highly ambiguous and commonly used outside the Jike context, so it may trigger the skill for unrelated requests. This raises the risk of unintended invocation and misrouting, especially because the skill is social-content oriented and not constrained by explicit platform references.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The term "圈子" is highly ambiguous and commonly used outside the Jike context, so it may trigger the skill for unrelated requests. This raises the risk of unintended invocation and misrouting, especially because the skill is social-content oriented and not constrained by explicit platform references.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal