ClawHub
Back to skill

Security audit

Sourcing in China

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed China-sourcing search helper that sends user search terms to an external MCP service, so users should avoid confidential queries and verify supplier results.

Install only if you are comfortable sending sourcing keywords, page numbers, and product URLs to the listed third-party MCP server. Do not include confidential product plans, proprietary specifications, target pricing, customer names, credentials, or personal data in queries, and independently verify supplier identities, certifications, prices, payment details, and links before making purchasing decisions.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:7
Finding

Untrusted Third-Party MCP Service Controls Sourcing Data

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger description is very broad, covering generic procurement and sourcing terms such as "source," "manufacturer," and "procurement." This can cause the skill to activate in contexts where the user did not intend to query an external China-sourcing service, increasing the chance of unnecessary external data transmission and irrelevant tool use.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
95% confidence
Finding

The skill explicitly instructs sending search keywords and product URLs to an unauthenticated third-party MCP endpoint over the network. Even though the content is described as public sourcing data, ambiguous activation or careless user queries could expose sensitive business intent, proprietary product interests, or internal procurement information to the external service.

Content

Scanner excerpt · SKILL.md (reported line 38)May include surrounding context.

md
SESSION=$(curl -sN https://mcp.chexb.com/sse | grep "^data:" | head -1 | sed 's/data: //')

# 2. Initialize MCP session
curl -s -X POST "https://mcp.chexb.com${SESSION}" \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"openclaw","version":"1.0"}}}'

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The instruction 'Use English keywords for best results' imposes a language preference in the skill guidance without offering a user choice or framing it as optional. Under the policy, language constraints should be opt-in or clearly justified as a documented limitation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.