知乎草稿写手 Zhihu Draft Writer

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:21 PM UTC
• Version:
  1.0.0

Overview

The skill is a disclosed Zhihu draft-writing automation, but users should understand it can control a logged-in browser, call a third-party AI endpoint, and create drafts in their account.

Install only if you are comfortable letting OpenClaw control a Chrome session logged into Zhihu and sending selected Zhihu page context to the documented AI endpoint. Use a dedicated browser profile if possible, review drafts manually before publishing, keep the API key revocable, and disable browser host control when finished.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The runtime options instruct the workflow to generate content and save it to the Zhihu draft box, but they do not require any explicit user confirmation or warning that a state-changing action will occur. In an agent setting, this can lead to unintended account modifications, surprising the user and normalizing silent write actions against a connected third-party service.

VirusTotal

60/60 vendors flagged this skill as clean.