ClawHub
Back to skill

Security audit

Bailian Search

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent web-search skill that sends user queries to Alibaba Cloud DashScope as advertised, with no hidden local access, persistence, or destructive behavior found.

Install only if you are comfortable using Alibaba Cloud DashScope for searches. Do not submit secrets, private internal data, or regulated personal information as search queries, and consider using a temporary environment variable instead of permanently storing the API key in a shell profile.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill clearly requires environment access for DASHSCOPE_API_KEY and network access to a remote SSE endpoint, but it does not declare an explicit permission or allowed-tools scope. This weakens least-privilege controls and makes it harder for users or hosting platforms to understand and constrain what the skill can access.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill states that it performs real-time web search through Alibaba Cloud Bailian, but the user-facing description does not clearly warn that submitted queries are sent to a third-party service. Users may unknowingly transmit sensitive prompts, internal data, or regulated information to an external provider, creating privacy and compliance risk.

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The embedded Python emits status and error messages in Chinese such as 'SSE监听', '错误: 无法建立MCP会话连接', and result labels, which imposes a specific language on users. This matches the language/locale policy violation category because the script does not provide opt-in, selection, or justification for the locale restriction.

External Transmission

Medium
Category
Data Exfiltration
Content
h2 = {'Authorization': f'Bearer {api_key}', 'Content-Type': 'application/json'}

# MCP握手
requests.post(msg_url, headers=h2, json={
    'jsonrpc':'2.0','id':0,'method':'initialize',
    'params':{'protocolVersion':'2024-11-05','capabilities':{},'clientInfo':{'name':'bailian-search','version':'1.1.0'}}
}, timeout=10)
Confidence
80% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
h2 = {'Authorization': f'Bearer {api_key}', 'Content-Type': 'application/json'}

# MCP握手
requests.post(msg_url, headers=h2, json={
    'jsonrpc':'2.0','id':0,'method':'initialize',
    'params':{'protocolVersion':'2024-11-05','capabilities':{},'clientInfo':{'name':'bailian-search','version':'1.1.0'}}
}, timeout=10)
Confidence
80% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
time.sleep(0.5)

# 搜索
requests.post(msg_url, headers=h2, json={
    'jsonrpc':'2.0','id':100,'method':'tools/call',
    'params':{'name':'bailian_web_search','arguments':{'query':query,'count':count}}
}, timeout=10)
Confidence
84% confidence
Finding
This request sends the user-supplied search query to an external third-party service. That is expected for a web-search skill, but it still creates a real privacy and data-handling risk because sensitive prompts, internal names, or secrets entered by a user could be transmitted off-platform without sanitization, minimization, or an explicit consent boundary in the script itself.

Missing User Warnings

Low
Confidence
93% confidence
Finding
The README instructs users to configure an API key and use the search tool but does not clearly disclose that user queries will be transmitted to an external Alibaba Cloud DashScope service. This creates a transparency and privacy risk because operators may unknowingly send sensitive prompts, internal terms, or regulated data to a third party.

Static analysis

No suspicious patterns detected.