ClawHub
Back to skill

Security audit

source-driven-development

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only skill tells an agent to verify framework-specific code against official documentation, with no hidden execution, persistence, or credential handling found.

Installers should know this skill may cause the agent to spend extra time reading dependency files and official docs before writing framework-specific code. Non-Chinese users may find the instructions less accessible, and users who care about provenance should verify the unproven claim that it is based on an Anthropic official skill.

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)

Hidden Instructions

High
Category
Prompt Injection
Content
---
name: source-driven-development
version: 1.0.0
description: "Drive development from authoritative source documentation and specifications"
Confidence
60% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
This markdown skill instructs the agent entirely in Chinese, including role, usage conditions, and workflow, but does not indicate that Chinese output is optional or limited to a Chinese-speaking context. That can violate language/locale policy because it effectively forces a specific language without user opt-in.

Static analysis

No suspicious patterns detected.