ClawHub
Back to skill

Security audit

Longxia Skill Scanner

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed remote scanner that sends a user-provided public GitHub URL to Longxia and does not execute the target repository.

Install this only if you are comfortable sending the public GitHub URL you provide to Longxia's remote scanning service. Do not use it with private repositories, credential-bearing URLs, internal links, or URLs containing sensitive query parameters.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The script sends the user-supplied GitHub URL to a third-party service at https://longxia.cool/api/scans, which is an external data transmission. Even though this behavior is consistent with the skill’s stated purpose, there is no runtime warning, consent prompt, or inline disclosure in the script itself, so users may unknowingly transmit private repository paths, sensitive URL tokens, or internal metadata if they misuse the tool.

External Transmission

Medium
Category
Data Exfiltration
Content
esac

  printf '{"url":"%s"}' "$github_url" |
    curl \
      --fail-with-body \
      --silent \
      --show-error \
Confidence
88% confidence
Finding
curl \ --fail-with-body \ --silent \ --show-error \ --connect-timeout 10 \ --max-time 60 \ --request POST \ --header 'Accept: application/json' \ --head

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.