ClawHub
Back to skill

Security audit

OpenClaw Risk Manager

Security checks for vulnerabilities and agentic risk

Overview

This is a simple finance guidance skill for portfolio risk analysis, with no executable code or hidden persistence, though its activation wording is broad.

Install only if you want advisory portfolio risk and trade-planning help. Treat any hedging, stop-loss, or position-sizing output as analysis to review yourself or with a qualified professional, and avoid letting broad finance conversations turn into personalized trading advice without clear inputs and user direction.

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
95% confidence
Finding

The skill description uses broad, proactive activation language such as 'Use PROACTIVELY' for general risk assessment and portfolio protection, which can cause the agent to invoke this skill in loosely related finance conversations without clear user intent. Overbroad routing increases the chance of inappropriate delegation, unintended financial guidance, and bypass of more suitable domain-specific or safety-constrained handling.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The 'Use this skill when' section is generic and effectively self-referential ('risk manager tasks or workflows'), which does not meaningfully constrain activation scope. In a financial context, vague triggering is more dangerous because the skill can be selected for broad investment-related conversations, leading to overreach into advice, risk calculations, or hedging recommendations without appropriate context or safeguards.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.