ClawHub
Back to skill

Security audit

Heikinashi

Security checks for vulnerabilities and agentic risk

Overview

This skill is a low-risk local reference script, though its Heikinashi content is generic and not very useful as a specialized finance reference.

Install only if you want a very basic static finance-reference stub. Do not rely on it for accurate Heikin Ashi trading formulas, interpretation, compliance, or risk guidance 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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The code is not malicious and does not access files, networks, or external resources. However, there is a clear description-behavior mismatch: the script brands itself as a Heikinashi finance reference tool, but the actual outputs are generic placeholder text that could apply to almost any finance topic. It lacks substantive Heikin Ashi-specific content such as candle formulas (e.g., HA open/close/high/low), chart interpretation, signals, or examples. Thus the primary purpose as implemented does not accurately represent the declared specialized description.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.