ClawHub
Back to skill

Security audit

macro-regime-detector

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed macro-analysis helper that uses the Finskills API and does not include code execution, persistence, or hidden local access.

Before installing, understand that the skill depends on Finskills and sends API requests using your FINSKILLS_API_KEY. Avoid including private portfolio holdings, personal financial details, or other secrets in prompts unless you are comfortable with how your agent and the external API provider may process related requests.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The README instructs users to configure an API key and use live third-party endpoints, but it does not explicitly warn that prompts, parameters, and requested market data queries may be transmitted to the Finskills service. This is a real transparency/privacy issue rather than an exploit primitive: users may unknowingly send sensitive investment context or proprietary portfolio-related questions to an external API.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

This markdown file instructs the skill to make multiple HTTP requests to the Finskills API and the activation criteria include questions about how the macro environment affects the user's portfolio. However, the description does not explicitly warn users that portfolio-related context or request metadata may be sent to an external service. For markdown files, omission of privacy-relevant warnings about external data handling is in scope.

Content

No source excerpt is available for this finding.