ClawHub
Back to skill

Security audit

Finance Claw

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent finance-answering skill that uses disclosed FinChain/FUSD sources and does not ship executable code, persistence, or hidden privilege behavior.

Installers should treat this as a finance information helper, not investment advice. Because it relies on remote and live sources for current figures, verify important rates, reserve data, and product availability through official FinChain/FUSD channels before acting.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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)

Anti-Refusal Statement

High
Category
Anti-Refusal
Content
## Language Policy

- Always respond in the user's language when it is clear.
- Default to `zh-HK` when the user's language preference is not explicit.
- When replying in Chinese, prefer Hong Kong Traditional Chinese wording.
- Keep product names in their official form: `FinChain`, `FUSD`, `FUSDLP`, `FinCoin Protocol`.
Confidence
70% confidence
Finding
Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The language policy imposes a default locale and wording preference without explicit user opt-in. This can violate language/locale policy because the skill may force Hong Kong Traditional Chinese for ambiguous requests rather than asking the user to choose.

Static analysis

No suspicious patterns detected.