Back to skill

Security audit

Mx Search

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Eastmoney financial search helper that sends queries to one external API and saves search results locally for reuse.

Install only if you are comfortable sending your financial search queries to Eastmoney's API using your MX_APIKEY. Avoid entering confidential internal research or account data, and periodically clean the local mx_search text and JSON outputs if the results are sensitive.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (8)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill declares capabilities that involve reading environment variables, writing files, and making network requests, but it does not explicitly constrain them with a permissions or allowed-tools policy. In an agent environment, this increases the chance of overbroad execution and makes review, sandboxing, and least-privilege enforcement harder, especially since the skill also handles API credentials and external transmission.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
92% confidence
Finding

The skill explicitly transmits user queries to an external third-party API endpoint, which is a real data egress event. In context this is expected functionality for a search skill, but it still creates privacy and confidentiality risk if users include sensitive prompts, account data, internal research, or non-public information in queries.

Content

Scanner excerpt · SKILL.md (reported line 41)May include surrounding context.

  • 凭据保护: API Key 仅通过环境变量 MX_APIKEY 在服务端或受信任的运行环境中使用,不会在前端明文暴露。
javascript
curl -X POST --location 'https://mkapi2.dfcfs.com/finskillshub/api/claw/news-search' \
--header 'Content-Type: application/json' \
--header 'apikey: YOUR_API_KEY' \
--data '{"query":"立讯精密的资讯"}'

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

This code performs an external network transmission of arbitrary user queries and includes an API key in the request headers. While calling a remote search API is core to the skill's purpose, it still creates a real data exposure boundary and should be treated as sensitive in environments where queries may contain confidential financial or investigative information.

Content

Scanner excerpt · mx_search.py (reported line 51)May include surrounding context.

python
"query": query
        }
        
        response = requests.post(self.BASE_URL, headers=headers, json=data, timeout=30)
        response.raise_for_status()
        return response.json()

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill sends user-supplied queries together with an API-authenticated request to a remote third-party service, but there is no explicit disclosure, consent mechanism, or data-sharing notice in the tool behavior itself. In a financial context, search terms may reveal investment interests, internal investigations, or sensitive event monitoring, making silent transmission more privacy-sensitive than a generic web lookup.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill is described as a search capability, but it also writes both extracted text and raw JSON results to disk by default. This creates unintended local data retention of user queries and potentially sensitive API-returned content, which expands the privacy and exposure surface beyond what a user would reasonably expect from a search-only tool.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The code automatically stores query results under a fixed local directory without any necessity established by the stated purpose of performing searches. Retaining both plain-text and raw JSON outputs can expose sensitive search terms, financial research content, or authenticated response data to other local users, later processes, or backup systems.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The natural-language content and usage instructions are presented only in Chinese, which can amount to forcing a specific language without user opt-in. The file does not state that the skill is region-specific or provide any alternative language option.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

User-facing strings throughout the file, including usage text, errors, status messages, and result formatting, are hard-coded in Chinese. The policy requires avoiding fixed language/locale behavior unless the user is given an explicit choice or the locale restriction is clearly justified.

Content

No source excerpt is available for this finding.