ClawHub
Back to skill

Security audit

Vision Bot

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward image-analysis connector that clearly sends image tasks to a third-party API, with no hidden code or persistence found.

Install only if you are comfortable sending image URLs, task text, and related image-derived data to aiprox.dev for processing. Avoid using it with private, regulated, confidential, or access-controlled images unless you trust that service and its retention claims.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (1)

External Transmission

Medium
Category
Data Exfiltration
Content
## Make Request

```bash
curl -X POST https://aiprox.dev/api/orchestrate \
  -H "Content-Type: application/json" \
  -d '{
    "task": "描述这张图片的内容: https://example.com/photo.jpg",
Confidence
86% confidence
Finding
The skill instructs users to send task contents, including image URLs and potentially sensitive image-derived data, to an external service at aiprox.dev along with a spend token read from the environment. This creates a real data-exfiltration and third-party exposure risk because user-provided inputs and authentication material are transmitted off-platform, and the skill encourages direct submission of arbitrary URLs for remote processing.

Static analysis

No suspicious patterns detected.