ClawHub
Back to skill

Security audit

on-chain analytics for evm contract

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed on-chain contract analysis helper that sends contract data to external analytics services, with no local code execution or hidden persistence found.

Install only if you are comfortable sending contract addresses, chain names, and any manually supplied ABI JSON to the external on-chain analysis service and having Dune queries or dashboard links created for later viewing. Avoid submitting proprietary or sensitive ABI data unless you accept that external processing and persistence.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill does not clearly warn users that contract addresses, ABI data, and AI-generated queries are sent to third-party services such as Etherscan, Dune, and an external dashboard service, and that decoded tables/queries may be saved externally. This creates a transparency and privacy risk because user-supplied artifacts, proprietary ABIs, or sensitive investigative targets could be disclosed or persisted outside the primary system without informed consent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger guidance is broad enough that the skill may be invoked for generic requests like 'what does this contract do' or 'analyze this contract' without strong routing constraints, increasing the chance of over-triggering in mixed workflows. In context, this can cause unintended transmission of user-supplied contract addresses and related analysis requests to external services, especially when the user did not explicitly consent to on-chain analysis or third-party processing.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.