ClawHub

Recon Quick

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed bug-bounty reconnaissance helper that runs bbot and nmap and saves local scan results, but it should only be used on authorized targets.

Install only if you are comfortable running bbot and nmap locally. These presets may contact target systems and create logs or alerts, so use them only for domains you are authorized to test, review bbot/nmap installation sources, and store recon outputs where sensitive target data is appropriate.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill invokes local Python scripts and external binaries (`bbot`, `nmap`) and writes results to disk, but it declares no permissions for shell execution, file reads, or file writes. This creates a capability/permission mismatch that can bypass user expectations and platform policy controls, especially for a recon tool that performs network scanning and stores outputs.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill performs active port scanning against user-supplied targets without any explicit notice, confirmation, or guardrails about network interaction. In a security-tool context this is somewhat expected, but undisclosed active scanning can still create legal, policy, and operational risk if a user runs it against unauthorized targets or in sensitive environments.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
This function initiates web probing and bbot activity that transmits target information and generates network traffic, but the script does not clearly disclose that behavior at the point of use. Because the skill is explicitly a recon tool, the context reduces suspicion of malice, yet the lack of transparent user warning still increases the chance of accidental unauthorized scanning or data disclosure to third-party services.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal