ClawHub
Back to skill

Security audit

Analyze Open Source

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a Chinese-language workflow for analyzing code repositories and does not include scripts, persistence, network fetching, or hidden data handling.

Install this if you want structured codebase walkthroughs and are comfortable with reports being produced in Chinese. Use it only on repositories you intend the agent to inspect, since its normal function is to read and summarize project files.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Confidence
98% confidence
Finding
The skill unconditionally requires all analysis output to be in Chinese, removing user choice and potentially conflicting with the user's requested language or accessibility needs. In a security-sensitive assistant context, hardcoded language constraints can degrade usability, hinder review by operators, and create opportunities for policy bypass or reduced oversight if reviewers cannot easily validate the output.

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The template is hardcoded entirely in Chinese and does not provide any mechanism to match the user's preferred language. In a code-analysis skill, this can cause inaccurate, unusable, or exclusionary output for users expecting another language, and may lead downstream agents or operators to misinterpret technical analysis.

Static analysis

No suspicious patterns detected.