ClawHub
Back to skill

Security audit

Web3Tech

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Web3Tech research helper that uses a disclosed API key and MCP tools for crypto project analysis without hidden execution, persistence, or data access.

Before installing, understand that research queries and project identifiers may be sent to the Web3Tech MCP/API service, and you will need to provide WEB3TECH_API_KEY. Treat outputs as research support rather than investment advice; the skill does not trade, manage wallets, or modify accounts.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

md
- Do not run deep tools on every candidate from a broad search.
- Stop once you have enough evidence for a defensible answer.

## Output Rules

- Evidence-first conclusions.
- Separate observed facts from interpretation.

Static analysis

No suspicious patterns detected.