Security audit

妙达网页抓取

Security checks for vulnerabilities and agentic risk

Overview

This skill only provides instructions for fetching and summarizing user-specified web pages, with no bundled code, persistence, or credential handling.

Installers should understand that this skill may cause the agent to fetch web pages through `miaoda-studio-cli`; use it for URLs you intend to retrieve, and prefer the search skill when you do not already have a specific URL.

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 (1)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The description embeds trigger phrases such as "总结网页", "提取网页内容", and "读取网页", which are broad natural-language requests that could match many ordinary user utterances beyond a narrowly scoped skill invocation. The file does not provide exclusion conditions or negative examples to clarify when this skill should not activate versus when search or other tools should be used.

Static analysis

No suspicious patterns detected.