ClawHub
Back to skill

Security audit

Macro Regime Detector

Security checks for vulnerabilities and agentic risk

Overview

This is a simple markdown skill for macro and crypto regime analysis, but its trading-style recommendations should be treated as informational rather than financial advice.

Install only if you want market-regime analysis as an informational aid. Do not treat its outputs as personalized financial advice, and independently verify market data and risks before making trades or using leverage.

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
  • 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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description explicitly offers portfolio positioning and crypto market context without any warning that outputs may influence financial decisions or that signals can be incomplete, delayed, or wrong. Because the skill frames recommendations like leverage, exiting risk, and stablecoin-only positioning as direct outputs, users may over-trust the advice and incur material financial harm.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The invocation examples are broad enough to trigger the skill for generic investment-advice queries such as whether to go long or short, extending its use beyond narrow macro-regime classification. In this context, that increases the chance the agent delivers actionable financial guidance without sufficient guardrails, disclaimers, or scope restriction.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.