ClawHub
Back to skill

Security audit

Pod AI

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Pod AI connector wrapper that can create outbound calls only after user-confirmed write payloads.

Before installing, understand that this skill can use your connected Pod AI account to place outbound calls. Review the generated call payload carefully and only approve write actions when the recipient, voice agent, and intended effect are clear.

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
91% confidence
Finding
The skill description says to use this skill for ANY Pod AI request and instead of calling the API directly, which creates an overly broad invocation scope. That can cause the agent to route all Pod AI-related tasks, including sensitive or state-changing operations like outbound call creation, through this skill without sufficiently narrowing when it should be used or requiring stronger preconditions for write actions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.