ClawHub
Back to skill

Security audit

区块链全能助手

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed blockchain assistance skill for market analysis, wallet review, DeFi risk comparison, and Solidity help, with no hidden execution or persistence behavior found.

Before installing, treat its market, DeFi, and contract outputs as educational assistance only. Verify prices, balances, transactions, and contract findings against trusted explorers and independent audits, and never provide private keys, seed phrases, wallet passwords, or signing permissions.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list is broad and includes highly common crypto terms such as BTC, ETH, DeFi, and blockchain, which can cause the skill to activate in ordinary conversations that are not asking for this capability. In a blockchain skill that can provide contract code, security guidance, and financial-risk analysis, accidental activation expands the chance of unsolicited high-impact advice being injected into unrelated contexts.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger list contains very broad, high-frequency terms such as BTC, ETH, DeFi, blockchain, and crypto, which are likely to activate the skill during ordinary conversation that is only loosely related to this specific capability. Because this skill can generate contract code, security guidance, and transaction-related advice, over-triggering increases the chance of unsolicited high-risk financial or coding output in the wrong context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The file presents the skill primarily in Chinese and frames invocation in Chinese-first terms, but it does not state that the user can choose their preferred language or locale. Under the policy, language constraints should be opt-in or explicitly offered as a choice unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description states that replies default to Chinese, which imposes a language choice without explicit user selection. While not directly a security flaw, this can cause misunderstandings in sensitive contexts like smart-contract auditing, wallet-risk analysis, or financial guidance, where language mismatch may lead to incorrect user actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.