ClawHub
Back to skill

Security audit

openclaw agent reputation

Security checks for vulnerabilities and agentic risk

Overview

This blockchain reputation skill is mostly coherent, but it can spend gas and make permanent reputation-affecting on-chain writes without clearly requiring explicit user confirmation first.

Install only if you are comfortable giving the skill access to a dedicated wallet key. Prefer a testnet-only wallet with minimal funds, avoid mainnet/private asset wallets, and require your agent to ask for explicit confirmation before any identity creation or attestation transaction.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Confidence
95% confidence
Finding
The example flow shows the agent proceeding directly to create an on-chain identity after a natural-language request, without an explicit confirmation step that a blockchain write will occur and gas will be spent. In a skill that requires a signing key and can target mainnet, this can normalize unsafe autonomous transaction behavior and lead users to trigger irreversible writes or incur costs without informed consent.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The attestation-writing tool is documented as a simple positive/negative record operation, but the description does not clearly warn that attestations become permanent on-chain records and can materially affect an agent's reputation. Because this is a blockchain reputation system, casual or mistaken use can cause lasting reputational harm and immutable public data publication.

Static analysis

No suspicious patterns detected.