ClawHub

article-writer

Security checks across malware telemetry and agentic risk

Overview

This skill is an article-writing workflow, but it can save drafts and publish to a WeChat Official Account without a clear final approval step.

Install only if you intend the agent to research online, save articles into the specified Obsidian vault, and publish through a WeChat Official Account. Before use, review the referenced wechat-toolkit skill, protect WECHAT_APP_ID and WECHAT_APP_SECRET, and require the agent to show the final draft and ask for explicit approval before saving or publishing.

SkillSpector

By NVIDIA
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 (2)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs the agent to save content to an Obsidian vault and invoke another skill to publish to a WeChat Official Account, but it does not require explicit user confirmation before these side effects occur. In an agent setting, this can cause unintended data persistence or external publication from a casual request to 'write an article,' which is a meaningful integrity and privacy risk.

Missing User Warnings

Low
Confidence
87% confidence
Finding
The skill references required WeChat credentials and publication prerequisites but provides no user-facing warning that external publishing depends on sensitive environment configuration. While it does not expose secrets directly, it normalizes use of privileged credentials for a publishing action without clear safeguards or confirmation, increasing the chance of unintended use of a configured account.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal