ClawHub
Back to skill

Security audit

Exa

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Exa search helper that sends user-entered searches or URLs to Exa using the user's API key.

Install only if you are comfortable sending searches, URLs, and requested page content to Exa. Do not include secrets, private source code, internal URLs, or confidential identifiers in queries, and keep EXA_API_KEY private.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The script transmits the user-provided query to Exa's external API without any user-facing disclosure at execution time. In a skill context, queries may contain sensitive code, internal identifiers, or proprietary documentation requests, so silent third-party transmission creates a real privacy and data-handling risk even if it is expected functionality.

External Transmission

Medium
Category
Data Exfiltration
Content
highlights: true
    }')

curl -s -X POST 'https://api.exa.ai/search' \
    -H "x-api-key: $EXA_API_KEY" \
    -H 'Content-Type: application/json' \
    -d "$PAYLOAD"
Confidence
91% confidence
Finding
curl -s -X POST 'https://api.exa.ai/search' \ -H "x-api-key: $EXA_API_KEY" \ -H 'Content-Type: application/json' \ -d

External Transmission

Medium
Category
Data Exfiltration
Content
highlights: true
    }')

curl -s -X POST 'https://api.exa.ai/search' \
    -H "x-api-key: $EXA_API_KEY" \
    -H 'Content-Type: application/json' \
    -d "$PAYLOAD"
Confidence
91% confidence
Finding
https://api.exa.ai/

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.