ClawHub
Back to skill

Security audit

Mx Finance Search

Security checks for vulnerabilities and agentic risk

Overview

This skill behaves like a disclosed Eastmoney financial-news search tool, with expected API-key use and local result saving controls.

Install only if you are comfortable sending financial search queries and the EM_API_KEY to Eastmoney's service. Use --no-save for sensitive research if you do not want returned content written locally, and use a revocable API key with an appropriate scope.

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
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • 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 (6)

Tainted flow: 'req' from os.environ.get (line 176, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/get_data.py (reported line 187)May include surrounding context.

python
)

    try:
        with urllib_request.urlopen(req, timeout=timeout_seconds) as resp:
            raw_body = resp.read().decode("utf-8", errors="replace")
    except urllib_error.HTTPError as exc:
        err_body = exc.read().decode("utf-8", errors="replace") if exc.fp else ""

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill documentation indicates use of sensitive environment variables, outbound network access, and local file writes, but it does not declare an explicit tool scope such as permissions or allowed-tools. This creates a governance gap: the runtime may grant broader capabilities than reviewers or users can easily audit, increasing the risk of unintended data access, exfiltration, or misuse of the API key.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
99% confidence
Finding

The top-level docstring explicitly states "no environment reads," which directly contradicts the implementation at L043-L046 that reads os.environ and aborts if EM_API_KEY is missing. This is an active documentation-to-code contradiction, not merely an omitted detail.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

User-supplied natural-language queries are sent to an external Eastmoney endpoint, but the transmission is not surfaced with an explicit user-facing warning at the point of use. In this skill context, queries may contain sensitive market research, internal watchlists, or investment intent, so undisclosed transmission to a third party creates a privacy and data-governance risk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill is presented as a search capability, but by default it persists remotely retrieved content to a local file under the current working directory. This can unexpectedly leave sensitive queries or returned financial content on disk, increasing exposure in shared environments, containers, or systems where local artifacts are collected or synced.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The code writes remote content to a local file by default without a strong user warning, beyond a --no-save opt-out. In finance workflows, retrieved content may include sensitive research context or regulated information handling concerns, so silent local persistence can create unintended data retention and secondary disclosure risks.

Content

No source excerpt is available for this finding.