ClawHub
Back to skill

Security audit

My Skill

Security checks for vulnerabilities and agentic risk

Overview

The skill is not malicious, but it asks an agent to make state-changing external API calls from vague trigger phrases, so users should review the scope before installing.

Install only if you intend this skill to call the Example API with MY_API_KEY. Use a least-privilege API token, verify every confirmation prompt before approving writes or deletes, and consider narrowing the trigger phrases and allowed actions before production use.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases include vague patterns such as “do the thing” and similarly broad intent matching, which can cause the skill to activate on ambiguous user input. Because this skill performs state-changing API actions, accidental activation could lead to unintended external requests or destructive operations even if a later confirmation step exists.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 30)May include surrounding context.

md
1. **解析意图**：从用户输入中提取必要参数（payload）。
2. **验证环境**：检查 `MY_API_KEY` 是否有效。
3. **安全拦截**：若涉及状态变更，调用确认函数（Confirm Function）。
4. **执行请求**：将请求发送至 `https://api.example.com/action`。
5. **反馈结果**：将 API 返回的 JSON 响应格式化后呈现给用户。

## 示例请求

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 38)May include surrounding context.

md
1. **解析意图**：从用户输入中提取必要参数（payload）。
2. **验证环境**：检查 `MY_API_KEY` 是否有效。
3. **安全拦截**：若涉及状态变更，调用确认函数（Confirm Function）。
4. **执行请求**：将请求发送至 `https://api.example.com/action`。
5. **反馈结果**：将 API 返回的 JSON 响应格式化后呈现给用户。

## 示例请求

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

Nearly all user-facing operational instructions and examples are written in Chinese, and the file does not state that language selection is optional or user-driven. This can constitute a language/locale policy issue when the skill appears to prescribe a specific language without opt-in.

Content

No source excerpt is available for this finding.