ClawHub
Back to skill

Security audit

risk-guard

Security checks for vulnerabilities and agentic risk

Overview

This skill provides disclosed investment risk-check guidance and does not install code, persist itself, or take direct trading actions.

Install this only if you want a Chinese-language investment risk-control helper that can retrieve market data and produce conservative pre-trade veto guidance. Treat its output as advisory, verify key numbers independently, and avoid relying on it as the sole basis for trading decisions.

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
  • 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
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger list includes broad, common phrases such as '止损线', 'veto', and 'stop loss', which can appear in ordinary financial discussions and cause the skill to activate outside its intended narrow context. Unintended invocation is risky here because the skill is designed to independently fetch market data and impose blocking decisions, so accidental activation can override user flow or cause unnecessary external tool usage.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description, procedural requirements, and mandated output template are written to require Chinese-language interaction and reporting, with no opt-in or fallback for user language preference. This can cause misunderstandings of risk decisions, stop-loss levels, or veto outcomes for users operating in other languages, which is especially dangerous in a financial risk-control context where precision and clarity are critical.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.