ClawHub
Back to skill

Security audit

Bank Compliance

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a banking compliance helper with no evidence of malware, hidden persistence, exfiltration, or destructive behavior, though its trigger phrases may be broad for a regulated topic.

Install this only if you want assistance with banking compliance, KYC, AML, or regulatory-report workflows. Because the topic is regulated and the activation phrases may be broad, confirm the skill is relevant before sharing sensitive customer, account, or compliance material, and treat its output as drafting support rather than legal or regulatory advice.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger list contains broad generic phrases such as 合规审查, 合规审核, 合规检查, and 合规风险 that can match many ordinary user requests unrelated to this specific banking skill. Overbroad activation can cause unintended routing into a high-stakes compliance workflow, increasing the chance of irrelevant guidance, data over-collection, or user confusion in regulated contexts.

Vague Triggers

Medium
Confidence
85% confidence
Finding
The trigger list uses very broad banking/compliance phrases such as '合规审查', '反洗钱', and '监管报告', which can match ordinary user requests and cause the skill to activate outside a narrowly intended scope. In a sensitive banking context, ambiguous invocation can route general workflow content into a specialized compliance-review skill unexpectedly, increasing the chance of over-collection, misclassification, or inappropriate handling of regulated information.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.