ClawHub
Back to skill

Security audit

搜索抓取全栈

Security checks for vulnerabilities and agentic risk

Overview

This is a clearly described search, page-fetching, research, and Chinese AI news skill with no executable code or hidden persistence.

Install this if you want a Chinese-oriented search, scraping, research, and AI-news helper. Be aware that search and scraping tasks may send your queries or requested URLs to external services, so avoid using it for private, authenticated, or sensitive pages unless you understand the underlying tool behavior.

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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description uses very broad trigger phrases such as '联网搜索、网页抓取、信息采集、研究调研、AI资讯、热点', which are common in normal user requests and can cause the skill to activate unintentionally. Because this skill performs networked search and page retrieval, overbroad activation expands the chance of unnecessary external access, data exposure in queries, or routing users into a more powerful tool than intended.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The description uses broad marketing language covering search, scraping, cross-validation, and AI news without defining activation boundaries, allowed targets, or user-consent constraints. In an agent ecosystem, vague trigger scope can cause unintended invocation for loosely related prompts and expand access to networked capabilities beyond what users expect.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The natural-language description forces a single language presentation with no opt-in or explanation of a region-specific requirement. Under the policy, language or locale constraints should either offer user choice or be clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The description states that the skill queries “中文 AI 资讯,” which indicates a fixed language/locale behavior. There is no accompanying language-choice mechanism or justification that this skill is intentionally region- or language-specific.

Content

No source excerpt is available for this finding.