ClawHub
Back to skill

Security audit

Use Circle Wallets

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Circle wallet-selection guide; its only notable issue is that its trigger wording is broader than Circle-specific use cases.

Install this if you want Circle-specific wallet selection guidance. Be aware that broad wallet-related prompts may steer the agent toward Circle options even when you wanted a vendor-neutral comparison, so ask explicitly for non-Circle alternatives when that matters.

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 (1)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger list is excessively broad for an auto-invoked skill, including generic phrases such as 'blockchain wallets', 'choose wallet', and 'create wallet' that can match many ordinary user requests outside the precise Circle wallet-selection context. This can cause incorrect or premature skill activation, steering users into Circle-specific guidance when they may need neutral or different wallet advice, which is a scope-poisoning/invocation integrity issue rather than a code-execution flaw.

Static analysis

No suspicious patterns detected.