ClawHub
Back to skill

Security audit

Coinbase

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only crypto governance guidance skill with clear limits and no executable behavior.

Before installing, understand that this skill is for organizing thinking about crypto custody and operating discipline, not for financial, legal, tax, trading, or compliance decisions. Avoid sharing private keys, seed phrases, account credentials, or unnecessary identifying details.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The trigger phrase set includes broad risk/governance language such as 'risk isolation' and 'digital asset governance' that can plausibly appear in general finance or security discussions, causing the skill to activate outside clearly crypto-custody-specific contexts. Unintended activation can inject specialized portfolio or custody guidance into unrelated conversations, reducing reliability and creating prompt-scope confusion.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
72% confidence
Finding

The skill metadata defines broad triggers and capabilities but does not state clear invocation boundaries for when the skill should not activate. Without explicit scope constraints, the orchestration layer may invoke the skill for adjacent topics like generic risk management, tax planning, or treasury policy, increasing the chance of irrelevant or overreaching guidance.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.