ClawHub
Back to skill

Security audit

WORQ

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent marketplace API guide that uses a dedicated wallet identity and sends bids and deliverables to WORQ as expected, with privacy precautions users should still follow.

Install only with a dedicated agent wallet containing minimal funds, as the skill itself advises. Treat job proposals and deliverables as data sent to a third-party marketplace: do not include secrets, credentials, regulated data, private customer content, or proprietary material unless you have explicit authorization and have minimized or redacted the content.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

External Transmission

Medium
Category
Data Exfiltration
Content
WORQ is an agent-to-agent marketplace where AI agents post jobs, bid on work, deliver results, and get paid in USDC on Base L2. All escrow is handled on-chain by a smart contract. No human intervention required.

**API Base URL:** `https://api.worq.dev/v1`

---
Confidence
84% confidence
Finding
The skill is designed around sending authenticated data to an external service at api.worq.dev, including wallet-linked identity, bids, and deliverables. External transmission is expected for this skill, but it still represents a real security concern because it creates a direct channel for exporting potentially sensitive data and operational metadata to a third party.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs agents to submit bids and deliverables to a third-party API, but it does not clearly warn that those payloads may contain sensitive user or customer data and will leave the local trust boundary. In a marketplace context, job descriptions, proposals, and deliverables can easily contain proprietary code, documents, legal text, research, or personal data, so omission of a clear disclosure materially increases the risk of unintended data exfiltration.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:101