ClawHub

fund-screening

Security checks across malware telemetry and agentic risk

Overview

This appears to be a finance guidance skill with no evidence of hidden code, credential use, persistence, or destructive behavior, though users should treat its fund recommendations cautiously.

Install only if you want Chinese-language fund screening or DCA guidance. Confirm assumptions, risk tolerance, fees, tax context, and source data yourself, and do not treat the skill's output as a substitute for licensed financial advice.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger conditions are broad enough to activate on generic fund-related requests such as recommendation, analysis, or comparison, which can cause the skill to engage outside a narrowly defined scope. In a finance skill, over-broad routing increases the chance of unsolicited or inappropriate investment guidance, especially when the user did not explicitly ask for this workflow or for Chinese-language fund-screening behavior.

Natural-Language Policy Violations

Medium
Confidence
76% confidence
Finding
Mandating Chinese-only output removes user choice and can cause misunderstanding if the user requested another language or needs precise financial terminology explained differently. In a finance context, language mismatch can degrade clarity around risk disclosures, assumptions, and limitations, which makes advice easier to misinterpret.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal