ClawHub
Back to skill

Security audit

WeChat MP Reader FZX

Security checks for vulnerabilities and agentic risk

Overview

The skill has a clear WeChat-article-saving purpose, but its code can fetch any user-supplied URL instead of enforcing the documented WeChat-only scope.

Review before installing. Use it only with trusted WeChat article links and run it in an environment whose outbound network access is constrained, because the code does not enforce the WeChat-only destination it documents. Expect Markdown files to be written locally, and do not rely on the --images option to save images locally.

A.I.G

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

Warning
Location
scripts/fetch_wechat_article.py:219
Finding

Unrestricted URL Fetching Enables Server-Side Request Forgery

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (6)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill documentation indicates capabilities involving outbound network access and local file writes, but it does not declare any tool scope such as permissions or allowed-tools. This creates an authorization and transparency gap: an agent or reviewer cannot easily constrain or audit what the skill is allowed to access, increasing the risk of unintended network fetches or writes beyond user expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The HTTP headers hard-code Accept-Language: zh-CN,zh;q=0.9,en;q=0.8, which imposes a specific language/locale preference for all requests. This is a natural-language policy concern because the skill does not offer user opt-in or explain why a Chinese locale is required.

Content

No source excerpt is available for this finding.

Tainted flow: 'filepath' from requests.get (line 268, network input) → open (file write)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · scripts/fetch_wechat_article.py (reported line 270)May include surrounding context.

python
filename = f"{safe_title}.md"
    filepath = os.path.join(output_dir, filename)

    with open(filepath, 'w', encoding='utf-8') as f:
        f.write(markdown)

    print(f'已保存: {filepath}')

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill is designed to fetch remote article content and save it locally, but the description does not clearly warn users that local storage occurs by default. This can lead to unintentional persistence of content on disk, which is a privacy and user-expectation issue, especially on shared machines or when handling sensitive article URLs.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
98% confidence
Finding

The module docstring and CLI help claim the tool supports downloading images locally, and fetch_article accepts a save_images parameter for that purpose. However, the function never uses save_images; it only preserves remote image URLs in generated Markdown and writes a single .md file.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
99% confidence
Finding

The --images argument is described as 下载图片到本地, which tells users the program will fetch and save article images locally. In reality, args.images is merely passed through to fetch_article, where it is ignored and no image download logic exists.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.