ClawHub
Back to skill

Security audit

my-test-skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a design-guidance prompt that broadly improves visual outputs, with no code execution, data access, persistence, or hidden external behavior.

Install this if you want visual artifacts to receive automatic design polish. Be aware it may influence many tasks with a visual component even when you did not explicitly ask for design help, so users who need strict task separation may prefer narrower activation rules.

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 (3)

Vague Triggers

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill declares that it should automatically activate for 'any visual output' request, which is an overly broad trigger that can hijack many normal user tasks involving reports, dashboards, HTML, PDFs, or visualizations. This can cause unintended behavior, hidden instruction precedence, and unexpected transformation of user requests even when the user did not ask for this skill, reducing predictability and increasing the chance of policy or workflow interference.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

描述文本以中文规定技能用途与行为，但文档中没有说明是否支持根据用户偏好切换语言，也未提供语言选择或 opt-in 机制。按规则，若技能强制特定语言/语言环境而无用户选择，属于自然语言策略风险。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger section includes broad, catch-all patterns such as requests to create pages, websites, visual presentations, HTML artifacts, or UI components, without concrete boundaries or exclusions. In a multi-skill or agent environment, this increases accidental activation and instruction collision risk, allowing this skill to override more specialized or safer workflows simply because a request has a visual component.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.