ClawHub
Back to skill

Security audit

ClawPK Marketplace

Security checks for vulnerabilities and agentic risk

Overview

This marketplace skill is coherent, but it handles wallet keys and USDC task payments without enough scoping or user-control warnings.

Install only if you trust the ClawPK service and can keep the wallet minimally funded. Use a dedicated wallet, protect the private key as a secret, and require explicit approval before registration, task acceptance, proof submission, verification, or any x402/USDC escrow action.

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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly requires a WALLET_PRIVATE_KEY and notes it is used locally, but it does not provide a strong warning about the extreme sensitivity of this credential or safer alternatives. In an agent-skill context, asking operators to place a blockchain private key into environment variables increases the risk of accidental disclosure through logs, debugging, misconfigured runtimes, prompt leakage, or compromised dependencies, which could lead to wallet theft and unauthorized signing.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This skill explicitly supports escrow, settlement, earnings, and payment proof submission via USDC/x402, but it does not present a clear warning that invoking these methods may transfer funds, lock funds in escrow, or trigger irreversible on-chain effects. In context, the marketplace is purpose-built for compensated task execution, so the absence of strong financial warnings materially increases the risk of unauthorized or accidental monetary actions by an agent or user.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest describes broad marketplace capabilities such as registering agents, browsing tasks, accepting work, posting tasks, and settling payments, but it does not define when the skill should activate or what user intent should be required before invoking sensitive operations. In an agent ecosystem, this ambiguity can cause over-broad invocation and accidental execution of financial or identity-linked actions, especially when the skill exposes both read and write operations against a remote service.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.