ClawHub

interbank-funding-trader

Security checks across malware telemetry and agentic risk

Overview

This is a finance workflow assistant with local collateral-check tooling, but it does not show hidden execution, credential theft, persistence, or data exfiltration.

Install only if you want Codex to assist with CNY interbank funding analysis and collateral-check workflows. Treat all plans and eligibility results as decision support: confirm real accounts, prices, limits, counterparties, collateral rules, and compliance requirements before using anything in an actual transaction.

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 (3)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The activation text is broad enough to match many generic requests about analysis, notes, procedures, market interpretation, or decision-making, which increases the chance the skill is invoked outside a clearly intended banking context. Over-broad triggering can expose sensitive domain-specific workflows and file-backed behavior in situations where the user did not intend to use this specialized skill.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill enables implicit invocation without any visible trigger constraints, so the agent may activate this finance-oriented workflow in response to loosely related prompts. In a banking/trading context, unintended activation is risky because it can cause the system to generate trader-style operational guidance, funding decisions, or eligibility judgments without the user explicitly requesting this specialized behavior.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger phrases are broad everyday expressions such as '帮我验券' or '这些券能不能押', which can cause the skill to activate in contexts the user did not explicitly intend. In a banking workflow skill, accidental activation is more dangerous because it may steer the agent into giving quasi-operational collateral eligibility judgments on incomplete or test data, increasing the risk of misleading financial decisions.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal