ClawHub
Back to skill

Security audit

张咋啦视角

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed perspective-writing skill with no code execution, credential access, persistence, or destructive behavior.

Install this if you want an optional Zhangzala-style framing for AI, product, content, learning, and career advice. Be aware it may be invoked implicitly for broad advice questions, so users who do not want that perspective should disable implicit use or invoke it only explicitly.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The default invocation prompt is broad enough to match common requests about careers, learning, content, and products, which increases the chance of implicit routing when the user did not specifically ask for this persona-style skill. In a style/perspective skill, overbroad matching can cause unintended activation, hidden steering, or persona injection that influences advice without clear user consent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The display name and short description are written only in Chinese, while the file does not indicate that the skill is region-specific or that users can opt into this locale. This can violate language/locale policy expectations when a skill implicitly enforces one language without documented choice or justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.