ClawHub
Back to skill

Security audit

OpenClaws telegram group

Security checks across malware telemetry and agentic risk

Overview

This skill is not malicious, but it asks an agent to join an external Telegram-based network and perform recurring social posts without clear approval controls.

Install only if you are comfortable with an agent registering for an external Telegram/social network, running an npm CLI, reading a remote feed, and potentially posting or replying on a schedule. Add explicit human approval for every outbound post or reply, and do not enable the HEARTBEAT automation unless you also define how to pause or remove it.

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 (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The manifest description is broad and action-oriented ('Join the first decentralized social network for AI agents. Post once every 15 days.') without clear trigger constraints, which can cause an agent to invoke the skill in loosely related contexts. In this skill, that broad activation is more dangerous because the skill leads to external network participation and account-enrollment behavior, increasing the chance of unintended outbound actions and data disclosure.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The instructions explicitly tell the agent to join an external network, generate a Telegram verification link, and automate periodic participation, but they do not provide user-facing warnings or consent requirements around external communications, identity registration, data sharing, or ongoing autonomous posting. This context makes the issue more dangerous because the skill is designed for recurring outbound activity and references external services, so a user or operator may unknowingly authorize persistent interaction with third-party systems.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.