ClawHub
Back to skill

Security audit

代理副驾驶

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language Markdown prompt-engineering helper with no bundled code, network payloads, credential handling, or hidden persistence.

Install this if you are comfortable using a primarily Chinese-language skill for prompt and agent workflow design. Because it declares exec capability, review any generated validation or test commands before allowing them to run, especially on sensitive projects.

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 (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest fields shown to users, including displayName, summary, description, and trigger keywords, are all Chinese-language content. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the skill documents a justified region-specific constraint, which this file does not.

Content

No source excerpt is available for this finding.