ClawHub
Back to skill

Security audit

search1api

Security checks across malware telemetry and agentic risk

Overview

This is a coherent web-search skill, with the main caution that searches and URLs are sent to an external Search1API service.

Install this if you want Search1API-backed web search and page retrieval. Avoid giving it sensitive private URLs, internal links, or confidential search terms unless you are comfortable sending that content to the Search1API service and any selected search engines. Review the CLI install and authentication method before use, especially if storing an API key locally.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The trigger guidance is broad enough to match many ordinary requests such as 'look up' or any bare URL, which can cause the skill to activate in situations where the user did not clearly intend to use an external web-search provider. In this skill's context, that increases the chance of unintended data disclosure to a third-party service and unnecessary tool use.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to send user queries and URLs to Search1API via MCP or CLI but does not warn that this transmits user-provided content to an external service. This is dangerous because users may share sensitive links, internal URLs, or private research terms without realizing they will be disclosed off-platform.

Natural-Language Policy Violations

Low
Confidence
71% confidence
Finding
The instruction to automatically route Chinese queries to specific engines imposes locale-specific behavior without asking the user which source or jurisdiction they prefer. While likely intended to improve relevance, it can alter privacy, censorship, and result-quality characteristics in ways the user did not request.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.