ClawHub
Back to skill

Security audit

妙达图片理解

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward image-understanding wrapper around a CLI command, with no bundled code, persistence, or hidden behavior found.

Install this if you want a CLI-backed image analysis skill. Be mindful that analyzing local screenshots or photos may expose their contents to whatever backend miaoda-studio-cli uses, so use it only with images appropriate for that tool.

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 trigger list includes very broad natural-language phrases such as '看图', '图片内容', 'describe image', and 'analyze image', which can overlap with ordinary user requests and cause the skill to activate too eagerly. Over-broad activation increases the chance of unintended tool use on local file paths or image-related requests, which can route sensitive user data into the CLI flow without sufficiently explicit user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

Nearly all user-facing instructions and examples are written only in Chinese, and the default prompt text is also Chinese, while the document does not state that users may choose another language. This can be a natural-language policy issue if organizational policy requires not forcing a specific language without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.