ClawHub
Back to skill

Security audit

Zhihu Topic Hunter

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow content-planning skill for generating Zhihu topic ideas, with no executable code, persistence, credential handling, or hidden high-impact behavior.

This skill appears safe to install for Zhihu content ideation. Be aware that it is optimized for Chinese Zhihu-style output and may browse current sources when you ask for recent or hot topics.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill hard-codes a Chinese-only output structure and labels without stating that this should depend on the user's language preference. This can override user intent or system-level expectations, creating prompt-quality and policy-compliance issues in multilingual environments, especially when an agent is expected to preserve the user's chosen language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The instruction text is written entirely in Chinese and requests Zhihu-specific topic generation, which implicitly constrains the interaction to a specific language/locale. There is no indication that the user may choose another language or that the language requirement is an opt-in preference.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.