ClawHub
Back to skill

Security audit

4d Compression Core

Security checks for vulnerabilities and agentic risk

Overview

This is a local markdown-only text compression skill with no executable payload, network behavior, persistence, or data exfiltration evidence.

Before installing, be aware that short words like "compress" or "压缩" may invoke the skill more often than expected. Install it only if you want a Chinese-oriented local text-compression helper, and consider adjusting triggers or priority if your agent supports that.

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

High
Confidence
96% confidence
Finding
The trigger phrases are extremely generic, especially "压缩", "4d", and "compress", and the metadata sets priority to "critical". This makes accidental invocation likely during normal conversation, which can cause the skill to intercept unrelated user requests and transform content without clear user intent or consent.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The manifest description, usage examples, and trigger guidance are entirely presented in Chinese, and the documented invocation examples assume Chinese-language commands. There is no statement that users may choose another language or locale, which can violate language-choice policy when the skill is not clearly limited to a Chinese-only context.

Static analysis

No suspicious patterns detected.