ClawHub
Back to skill

Security audit

用于快速产出**架构图 / 流程图 / 时序图 / 部署图**等可视化交付物，常见输出为 `.svg`（可离线打开）或 `.html`（浏览器直接预览）

Security checks across malware telemetry and agentic risk

Overview

This is a coherent diagramming skill, but public Kroki/CDN rendering can expose diagram contents or browser request metadata to third parties.

Install only if you are comfortable with a diagramming skill that may use external rendering services. For private architecture diagrams, set --kroki-url to a trusted internal Kroki instance or use local/offline SVG generation, and avoid opening the CDN-backed HTML preview when third-party network access is not acceptable.

SkillSpector

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

Missing User Warnings

Low
Confidence
80% confidence
Finding
The page imports executable JavaScript from a remote CDN at runtime without any disclosure, which creates a supply-chain trust dependency and causes user data such as IP address and request metadata to be sent to a third party. If the CDN, package, or delivery path is compromised, opening the local HTML file could execute attacker-controlled code in the browser.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The script sends the full diagram source to a remote Kroki endpoint by default (`https://kroki.io`) without any explicit warning, confirmation, or opt-in. In an agent skill context, users may supply proprietary architecture diagrams, internal hostnames, credentials accidentally embedded in diagrams, or other sensitive design data, so silent network exfiltration to a third-party service creates a real confidentiality risk.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.