ClawHub
Back to skill

Security audit

Another WeChat Article Reader

Security checks across malware telemetry and agentic risk

Overview

This skill has a clear WeChat article-reading purpose, but it should be reviewed because one fallback script can fetch arbitrary hosts and the network dependency/scoping story is under-controlled.

Install only if you are comfortable with a skill that runs local HTTP-fetch scripts. Prefer using the main script on public mp.weixin.qq.com article URLs only; avoid using the diagnostic fallback on arbitrary URLs until it adds the same host validation and safer redirect handling.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill explicitly instructs the agent to fetch external WeChat article URLs via a dedicated script, which is a network-capable operation, but no permissions are declared in the skill metadata. Undeclared network access weakens policy enforcement and review because the skill can access remote content while appearing less privileged than it really is.

Known Vulnerable Dependency: curl_cffi — 3 advisory(ies): GHSA-3vpc-4p9p-47hc (curl_cffi bundles a version of libcurl affected by High Severity vulnerability); CVE-2026-33752 (curl_cffi: Redirect-based SSRF leads to internal network access in curl_cffi (wi); CVE-2026-33752 (curl_cffi: Redirect-based SSRF leads to internal network access in curl_cffi (wi)

Critical
Category
Supply Chain
Confidence
94% confidence
Finding
The project pins a dependency on curl_cffi, and the supplied finding indicates multiple advisories affecting that package, including a critical redirect-based SSRF issue. In this skill’s context, the package is used to fetch user-supplied WeChat article URLs, which makes network request handling security-sensitive; if redirects are not safely constrained, an attacker could potentially pivot requests toward internal or unintended endpoints.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.