ClawHub
Back to skill

Security audit

Market Pulse Wingman

Security checks for vulnerabilities and agentic risk

Overview

This is a simple market-analysis instruction skill with no executable code, persistence, credential access, or hidden data handling.

Before installing, understand that this skill can ask for trading context and may rely on current market/news sources, so avoid sharing account credentials or private financial details you do not want used in analysis. Treat its output as decision support, not guaranteed financial advice.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Content
---
name: market-pulse-wingman
description: Market risk co-pilot for equities. Use when you need to scan a watchlist for technical context, fresh headlines, and operational/security red flags, then log a disciplined trading recommendation with follow-up notes.
emoji: "🕵️‍♂️"
---

# Market Pulse Wingman

## Overview
Use this skill when the user wants a fast but disciplined read on one or more tickers. It blends the day-trading workflow (trend, catalysts, sizing) with a security-auditor pass over current headlines and finally writes a short log entry for the self-improvement tracker.

## Quick start
1. **Collect co
Confidence
80% confidence
Finding
YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Context Leakage

High
Category
Data Exfiltration
Content
Use this skill when the user wants a fast but disciplined read on one or more tickers. It blends the day-trading workflow (trend, catalysts, sizing) with a security-auditor pass over current headlines and finally writes a short log entry for the self-improvement tracker.

## Quick start
1. **Collect context** from the user:
   - Tickers (and optional notes: position size, time horizon, risk tolerance)
   - Any data they already have (price, % change, headlines). If nothing is provided, ask for a watchlist snapshot or proceed with publicly available info.
2. **For each ticker**, run the structured workflow below and append the result.
Confidence
75% confidence
Finding
Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

Static analysis

No suspicious patterns detected.