Back to skill

Security audit

WeChat Article Fetcher

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it claims: it fetches WeChat article text through a disclosed third-party URL conversion service, with a privacy caveat for article links.

Install only if you are comfortable with WeChat article links being sent to down.mptext.top for processing. Avoid using it with private, access-controlled, or token-bearing links unless the URL is sanitized or you trust that third-party service.

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
SKILL.md:14
Finding

Disclosure of Complete User-Supplied URLs to a Third-Party Service

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, line 14; supporting workflow instructions at lines 26–28
Vulnerability Type: Third-party URL disclosure without sanitization or explicit consent
Risk Level: Medium

Vulnerable Code

bash
curl -s "https://down.mptext.top/api/public/v1/download?url=<URL_ENCODED_LINK>&format=markdown"

The supporting workflow at lines 26–28 instructs the agent to:

text
1. Extract the WeChat article link from the user message
2. URL-encode the link
3. Call the API to retrieve its content

Technical Analysis

The skill submits the complete user-supplied WeChat article URL to the unrelated third-party domain down.mptext.top. The instructions require URL encoding, but encoding only converts characters into a transport-safe representation; it does not redact query parameters, access tokens, tracking identifiers, or other sensitive values.

No instruction requires the agent to remove unnecessary query parameters, reject embedded credentials, validate the URL after parsing, inform the user of the external disclosure, or obtain explicit consent. Consequently, sensitive data contained in a URL can be transferred to and potentially logged by the third-party service and its supporting infrastructure.

Attack Path

  1. A user supplies an mp.weixin.qq.com article URL containing sensitive query parameters, tracking identifiers, or temporary access values.
  2. The skill extracts the complete URL from the message.
  3. The skill URL-encodes the complete value without removing sensitive components.
  4. The agent executes the documented curl request.
  5. The encoded URL is transmitted as the url query parameter to down.mptext.top.
  6. The third-party operator, reverse proxies, network monitoring systems, or request logs can observe and retain the disclosed URL data.

Impact Assessment

Exploitation does not grant local system privileges, code e ...[truncated 399 chars]

Remediation
View remediation

Remediation Suggestions

  1. Parse each supplied URL with a structured URL parser rather than interpolating raw user input into the request.
  2. Permit only HTTPS URLs whose normalized hostname is exactly mp.weixin.qq.com or belongs to an explicitly documented allowlist.
  3. Reject URLs containing embedded credentials, unexpected ports, fragments, malformed encodings, or disallowed schemes.
  4. Define an allowlist of query parameters required to retrieve an article and remove all other parameters before transmission.
  5. Specifically redact access tokens, signatures, user identifiers, tracking values, and other sensitive parameters.
  6. Clearly disclose that the sanitized URL will be sent to down.mptext.top and obtain user consent before making the request.
  7. Prefer direct retrieval from the original WeChat host where technically and legally feasible, avoiding unnecessary third-party disclosure.
  8. Avoid recording full request URLs in application logs. If logging is required, log only the normalized hostname and a non-sensitive request identifier.
  9. Enforce request timeouts, response-size limits, and content-type validation when processing the third-party response.
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs the agent to send a user-provided WeChat article URL to an external third-party service (down.mptext.top) to retrieve content, but it does not disclose that the link will be shared off-platform or discuss privacy implications. Even if the URL itself seems harmless, article links can contain tracking parameters, private/unlisted content references, or reveal user interests and activity to the third party.

Content

No source excerpt is available for this finding.