ClawHub
Back to skill

Security audit

Clawdbot Release Check

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed release-checker that optionally installs a daily notification job, with no evidence of hidden data theft or destructive behavior.

Install this if you want clawdbot release notifications. Only run setup.sh if you want a persistent daily check, verify the notification channel and recipient before enabling it, and use setup.sh --uninstall when you no longer want the scheduled job.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding
The skill advertises shell-based installation and execution steps (`setup.sh`, `check.sh`) but declares no permissions, so users and security tooling are not clearly informed that it can execute local scripts and modify the system. That lack of transparency increases risk because the skill can perform actions such as scheduling jobs and writing state files without an explicit permission boundary.

Tp4

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding
The documented behavior goes beyond a simple release check: it installs or removes scheduled jobs, configures outbound notification channels, and persists scheduler/cache/state data. This description-behavior mismatch is dangerous because users may grant trust based on a narrow stated purpose while the skill performs broader actions that affect persistence and exfiltration paths via messaging integrations.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.