ClawHub

小宿智能搜索

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward XiaoSu web-search skill that sends user searches to the XiaoSu API using a user-provided key.

Use this skill only for searches you are comfortable sending to XiaoSu's service. Avoid putting secrets, private customer data, or sensitive internal project names in queries, and prefer a dedicated API key stored in OpenClaw's environment configuration rather than hardcoding it.

SkillSpector

By NVIDIA
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)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger phrases are very broad, including common requests like 'search the web', 'look up', and 'search for', which can cause the skill to activate on many routine user prompts. In a skill that sends queries to an external service, unintended invocation can leak sensitive user content or cause actions to occur without sufficiently specific user intent.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The documentation instructs users to provide an access key and endpoint and shows direct transmission of queries to an external API, but it does not include a clear warning that user queries and possibly extracted content will leave the local environment. In a search skill, prompts may contain confidential research terms, internal names, or personal data, so the missing disclosure raises privacy and credential-handling risks.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The script sends user-supplied search queries, and optionally requests extracted page content, to a third-party remote search API without any explicit privacy notice or consent mechanism. In a skill context, users may provide sensitive prompts or investigative topics, so silent transmission can expose confidential data to the external provider and create compliance/privacy risk.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal