ClawHub
Back to skill

Security audit

Zhihu

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Zhihu connector skill that uses the OOMOL oo CLI for disclosed read/search/chat actions, with no packaged executable code or hidden persistence.

Install only if you are comfortable using OOMOL's oo CLI and connecting your Zhihu account through OOMOL. Review prompts before sending sensitive queries to the connector, and require explicit confirmation for any future write or destructive action if the connector adds one.

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
84% confidence
Finding
The skill description mandates use for ANY Zhihu-related request, which is broader than necessary and can cause the agent to invoke this skill even when a simpler or safer native method would suffice. Overly broad routing increases the chance of unintended tool use, unnecessary external data access, and user-surprising behavior, though this particular skill appears limited to read-oriented actions and documented connector usage.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.