ClawHub
Back to skill

Security audit

知乎回答生成器

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only writing helper for Zhihu-style answers, with no code execution, persistence, credential access, or hidden system behavior found.

Reasonable to install as a writing template skill. Before publishing generated content, verify statistics, case studies, screenshots, earnings claims, testimonials, and platform-policy compliance; avoid presenting illustrative examples as real personal results.

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
  • 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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly promotes 'data/case support' and lead-generation tactics but provides no guardrails requiring source verification, disclosure of anecdotal claims, or prohibition on invented metrics/examples. In a content-generation skill, this creates a material risk of fabricated authority, deceptive marketing, and misinformation being produced at scale, especially because the example includes unverifiable personal performance claims and conversion-oriented CTA patterns.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The activation section says to trigger whenever the user mentions phrases like “知乎回答” or “知乎文案,” but it does not define boundaries for when the skill should not activate. These terms are broad enough to appear in ordinary discussion about Zhihu content, creating ambiguity about intended invocation scope.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.