ClawHub
Back to skill

Security audit

天枢系统灵魂

Security checks across malware telemetry and agentic risk

Overview

This is a text-only stock-analysis philosophy skill with no executable code or account access, but its investment language should be treated cautiously.

Install only if you want an agent to reason in this stock-prediction style. Treat predictions and buy/avoid labels as informational, not professional financial advice; verify market assumptions, especially A-share color conventions, and do not allow any agent using this skill to place trades or manage accounts automatically.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill presents explicit buy/caution/forbidden-style trading guidance and frames itself as a disciplined prediction and execution system, but it does not include a clear financial-risk disclaimer, uncertainty notice, or non-advisory boundary. In a financial context, this can cause users to over-trust the output as personalized or authoritative investment advice, increasing the risk of harmful financial decisions.

Natural-Language Policy Violations

Medium
Confidence
81% confidence
Finding
The skill hard-codes A-share conventions such as red-up/green-down and presents them as the default design without clear locale scoping or user choice. While not a classic security flaw, this can mislead users operating in other markets, causing interpretation errors in a high-stakes financial setting where color and market conventions materially affect decision-making.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.