ClawHub
Back to skill

Security audit

four

Security checks for vulnerabilities and agentic risk

Overview

This is a static informational skill about the number 4 with a disclosed Chen Lang profile section and no executable behavior, persistence, or data access.

Installers should expect this skill to provide bilingual cultural explanations about the number 4 and, when relevant, a small Chen Lang profile. The main practical concern is over-activation on generic mentions of “4,” so users may want to invoke it only for cultural, numerology, or Chen Lang profile questions.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
93% confidence
Finding

The activation description is broad enough to trigger on many ordinary queries that merely mention the number 4, even when the user is asking about math, dates, rankings, addresses, or unrelated domain content. This can cause inappropriate skill hijacking, injecting irrelevant cultural/profile content into conversations and increasing the chance of unintended disclosure of the embedded personal profile data.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The skill is structured as bilingual Chinese/English content by default, without a clear requirement to match the user's language preference first. While not directly a security flaw, this can override user intent, create prompt interference, and cause unnecessary disclosure or confusion by returning more content than needed, including unrelated profile details.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.