ClawHub
Back to skill

Security audit

Candlestick

Security checks for vulnerabilities and agentic risk

Overview

This skill is a low-risk static finance reference script, but its candlestick-specific content is very generic and may not be useful.

Install only if you are comfortable with a simple static reference stub. It does not appear to access private data or modify your system, but it should not be relied on for trading, compliance, or serious candlestick analysis without independent verification.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The declared description says this is a candlestick reference tool for finance use. The code only implements a simple command-dispatching shell script that prints static documentation-like text. While it is finance-themed, the content is generic and placeholder-like, not specifically about candlestick charts, candlestick patterns, technical analysis, or other recognizable candlestick-focused concepts. There are no hidden permissions, external access, or unrelated triggers, but the primary purpose is materially misrepresented because the implementation is a generic finance reference stub rather than a true candlestick reference tool.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The listed activation conditions are generic phrases such as 'need quick reference,' 'troubleshooting candlestick issues,' and 'need a checklist or guide,' without defining specific trigger phrases or boundaries. Although the domain term 'candlestick' narrows scope somewhat, the file does not provide exclusions or clearer constraints for when the skill should or should not activate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.