ClawHub

Threat Intelligence — التهديدات

Security checks across malware telemetry and agentic risk

Overview

This skill performs the advertised passive threat-intelligence lookups, with some overbroad declared local permissions users should notice.

Install only if you are comfortable with a skill running local command-line network tools and sending OSINT queries or target domains to public and Tor-accessible services. Consider limiting local file read/write access because the included script does not appear to need it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill declares powerful tool requirements including `exec`, `read`, and `write`, and the static analyzer also detected shell-like capability, but there is no explicit permission model or constraints describing what commands may be run. In an agent environment, undocumented shell access materially increases risk because a user invoking an OSINT skill could unintentionally grant the skill the ability to run arbitrary local commands, access files, or alter the workspace.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal