ClawHub
Back to skill

Security audit

avavox 智能外呼

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Avavox outbound-calling skill that uses an App Key and customer phone data for its stated purpose, with no hidden persistence or off-domain behavior found.

Install only if you intend to let the agent manage Avavox outbound-call workflows. Store the App Key in protected OpenClaw credential or environment injection when possible, avoid hardcoding real keys in config.json, and require explicit review of phone-number lists, schedules, robot selection, line selection, and concurrency before importing customers or resuming calls.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
82% confidence
Finding
The skill documentation describes capabilities to read configuration files, consume environment variables such as AVAVOX_APP_KEY, and make outbound network requests, but no explicit permissions model is declared. That mismatch can cause an agent platform or reviewer to underestimate what the skill can access, increasing the chance of secret exposure or unintended network use when the skill is installed and executed.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.