ClawHub
Back to skill

Security audit

Exa Search

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Exa search helper that sends user-chosen searches to Exa with an API key and shows no hidden or unrelated behavior.

Install this if you intend to use Exa search and are comfortable setting an EXA_API_KEY. Do not include secrets, credentials, private business data, or regulated personal information in searches, because queries are transmitted to Exa when the script is invoked.

SkillSpector

By NVIDIA
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
86% confidence
Finding
The trigger description is broad enough to activate on generic requests like enabling search, configuring an API key, or performing web search, which can cause the skill to run in situations the user did not explicitly intend. In an agent setting, ambiguous activation increases the chance of unnecessary external network access and use of sensitive configuration flows, especially because the skill depends on an API key and a local script invocation.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.