ClawHub
Back to skill

Security audit

Crypto Paper Analyzer

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill is purpose-aligned for crypto whitepaper research, but users should treat its investment scores and buy/hold/sell language as research prompts rather than financial advice.

Install only if you want a research assistant for public crypto whitepapers. Do not rely on its scores, allocation suggestions, or buy/hold/sell recommendations as personalized financial advice; add your own risk, jurisdiction, portfolio, and due-diligence checks before acting.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
The checklist includes an explicit unqualified investment recommendation threshold: '>4=Strong buy signal'. In a skill designed to analyze crypto whitepapers and generate investment memos, this can cause the agent to present financial advice as a deterministic output without suitability, jurisdictional, or risk disclaimers, increasing legal, compliance, and user-harm risk.

Static analysis

No suspicious patterns detected.