ClawHub
Back to skill

Security audit

Feature Implementation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed TDD feature-implementation workflow that edits project code and docs only as part of the user-requested development task.

Install this if you want an agent to actively implement planned feature stages in your repository. Before using it, make sure the referenced specs and task-planning documents are correct, because the skill is intended to edit code, run tests, update planning files, and create development reports.

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

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill advertises very broad trigger phrases such as '开始写代码' and '实现XX阶段', which can easily match ordinary development requests that were not meant to invoke this specific high-impact workflow. Because the skill is designed to read project documents, create tasks, modify code, run tests, and potentially use browser/database tooling, accidental activation can cause unintended autonomous actions in the wrong context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description and all user-facing instructions are written to operate in Chinese, including fixed Chinese trigger phrases and output artifact paths, with no indication that the user can choose another language. This creates a language policy issue because the skill appears to enforce a specific language/locale without opt-in or a documented region-specific justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.