ClawHub
Back to skill

Security audit

Crypto Macro Regime Classifier

Security checks for vulnerabilities and agentic risk

Overview

This skill is not malicious, but it should be reviewed because it gives unqualified crypto trading and portfolio-allocation guidance.

Review this skill carefully before installing. It appears to be a simple informational Markdown skill, not malware, but its outputs may sound like actionable crypto investment advice. Use it only for market context, not as the sole basis for trades, allocation changes, or personalized financial decisions.

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

High
Confidence
97% confidence
Finding
The skill explicitly provides trading bias, asset-specific adjustments, and recommended portfolio allocation percentages, but does not warn that outputs are informational, probabilistic, and not financial advice. This omission is dangerous because users or calling agents may over-trust the output as prescriptive investment guidance, leading to harmful financial decisions, especially given the volatile and noisy nature of crypto sentiment and macro indicators.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The usage examples are overly broad and encourage invocation for open-ended trading decisions like whether to go long BTC, without narrowing when the skill should or should not be used. In an agent environment, this increases the chance the skill is applied automatically in high-stakes financial contexts and its outputs are treated as action-driving recommendations rather than limited market context.

Static analysis

No suspicious patterns detected.