Back to skill

Security audit

Claw Trade Hub

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent trading client, but it exposes high-impact marketplace actions with weak transport and authorization safeguards.

Review before installing or using against a real marketplace. Use only a trusted Hub endpoint, prefer wss:// for remote connections, require server-side authentication and authorization for every state-changing message, and treat direct transaction creation as unsafe unless the Hub validates it from accepted bids or negotiations.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
trade_client.py:15
Finding

Unauthenticated Cleartext WebSocket Trading Protocol

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The natural-language content of the skill, including the description and instructions, is presented in Chinese only. This can constitute a language policy violation when a skill effectively forces a specific language without user opt-in or an explicitly documented regional justification.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

This markdown file documents operations such as listing_cancel, listing_cancel_batch, bid_accept, negotiation_accept, and transaction_create, which can change marketplace state or finalize transactions, but it does not include any user warning about irreversible or data-affecting consequences. Under the markdown variant of SQP-2, descriptions should warn when behavior could affect user data or system integrity.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This code establishes a WebSocket connection and later sends listing, bid, negotiation, and transaction data over the network, but the file provides no user-facing warning beyond a generic connection log. The docstrings describe functionality, but they do not disclose that user-supplied trade details and participant identifiers will be transmitted to an external service.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The client exposes a public method that can directly emit a transaction_create message with arbitrary buyer_id, seller_id, listing_id, and price. In a trading system, transaction creation should be derived server-side from validated bid/negotiation acceptance flows; allowing the client to initiate it directly enables forged or inconsistent transaction records if the server trusts client messages.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The docstring explicitly says transaction creation is 'internal use', but the method is publicly callable and sends the message over the websocket without access control, confirmation, or integrity checks. This mismatch increases the chance that downstream developers or agents will call it as a supported action, potentially creating fraudulent transaction entries or bypassing intended business workflow controls.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
74% confidence
Finding

The file declares HUB_URL and the examples show connecting to a websocket server and sending listing, bid, negotiation, and transaction data, but the markdown does not warn users that business data will be transmitted over the network. For markdown files, networked behaviors that may affect privacy should be disclosed.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The module and class docstrings are written entirely in Chinese, and the skill does not indicate that language selection is configurable or that the locale restriction is intentional for a region-specific use case. Under the policy, forcing a specific language without opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.