zhihu-ops

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Zhihu browser-automation skill for account actions like liking, commenting, posting, and editing, with no executable code or hidden data flow found.

Install only if you are comfortable letting an agent use your logged-in Zhihu browser session for visible account actions. Give explicit Zhihu URLs or page context, confirm public posts, edits, comments, and replies before submission, and deny skill-file write-back if you do not want page-structure notes saved.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The skill trigger description is broad enough to match ordinary user phrases like '点个赞' or '评论一下', which can cause the skill to activate in contexts where the user did not clearly intend browser automation on Zhihu. Because this skill performs authenticated social actions such as liking, commenting, replying, and publishing, accidental invocation can lead to unintended account actions and public content changes.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal