ClawHub
Back to skill

Security audit

Wechat Freepublish

Security checks across malware telemetry and agentic risk

Overview

This is a small disclosed WeChat publishing helper that can post a draft publicly only when given a media_id and access token.

Install only if you intend to let an agent submit WeChat Official Account drafts for publication. Verify the media_id yourself, use the narrowest practical WeChat token, and require an explicit final confirmation before running the publish command because successful execution may immediately push the article to followers.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill invokes a Python script that uses both environment variables and network access, but the skill manifest does not declare those capabilities as permissions. This creates a transparency and governance gap: the agent may access sensitive credentials and perform external actions without explicit permission scoping or user-visible declaration, which is especially risky here because the action triggers irreversible public publication to a WeChat audience.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
scripts/publish.py:72