ClawHub
Back to skill

Security audit

Trading

Security checks for vulnerabilities and agentic risk

Overview

This trading education skill is coherent and disclosed, with guardrails against direct financial advice or trade execution.

Before installing, understand that this skill is for trading education and analysis only, not licensed financial advice. Enable the ~/trading memory or journal files only if you want persistent local notes, and do not use the skill to make trades without independent research or professional advice where appropriate.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (5)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% 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.

Content

Scanner excerpt · legal.md (reported line 111)May include surrounding context.

md
Does not provide "investment advice" as defined under MiFID II. Information is general and does not account for individual circumstances.

### General
Users must comply with all applicable laws in their jurisdiction.

---

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · memory-template.md (reported line 18)May include surrounding context.

md
## Learning Progress

### Mastered
<!-- Concepts user demonstrates understanding of -->

### Currently Learning
<!-- Active focus areas -->

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The 'When to Use' section says the skill applies whenever a user wants trading analysis or education, then lists a very wide range of topics. Because it does not define concrete invocation phrases, constraints, or negative examples, the trigger scope is ambiguous and could overlap with general finance conversations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The file requires that 'legal.md' disclaimers be shown on first use, but this file does not indicate that the disclosures should match the user's preferred language or locale. Since language/locale policy violations can arise when a skill forces content presentation without user opt-in or choice, this is a minor policy concern.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly instructs creation of files under ~/trading on first activation, which causes persistent local writes without any user notice or consent mechanism in the template itself. While the files are limited to trading notes and not obviously sensitive system paths, silent persistence can still surprise users and create privacy or trust issues.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.