ClawHub
Back to skill

Security audit

SZZG007 Web Deep Research

Security checks for vulnerabilities and agentic risk

Overview

The skill is openly a web research tool, but its customer background-check use case is broad and under-scoped for sensitive business and personal profiling.

Review before installing if you may use it for customer or decision-maker background checks. Limit it to authorized business research, avoid sensitive personal or credit information unless you have a lawful basis, and require explicit user confirmation before broad multi-platform searches.

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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises full-web research and customer background investigation but does not clearly disclose that it may access external platforms, process personal or company-related data, and aggregate information from multiple sources. In this context, missing notice and consent boundaries is dangerous because users may unknowingly trigger collection, enrichment, or profiling activity involving sensitive personal or reputational data.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrases are broad, everyday expressions such as market research and background-check requests, which can cause the skill to activate unintentionally in normal conversation. Because this skill can initiate wide external research across many platforms and produce potentially sensitive profiling output, accidental invocation increases privacy, data-handling, and unwanted external access risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

配置中将 WEB_RESEARCH_LANG 默认设为 zh-CN，且全文未说明用户可以选择其他语言，也未将该技能明确限定为仅服务中文区域或出于合规原因必须使用中文。根据规则，强制或默认固定语言而无用户选择属于语言/locale 策略问题。

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.