Back to skill

Security audit

PropAI Live

Security checks across malware telemetry and agentic risk

Overview

This skill is not clearly harmful, but it needs review because it directs agents toward real WhatsApp, Meta, lead-storage, and spending workflows through dependencies and a CLI that are not included or scoped in the submitted artifact.

Install only if you trust the publisher and can verify the propai-live CLI plus the listed dependency skills. Use a trusted license API URL, protect the local license state file, and require explicit confirmation before any live message, social post, lead write, or spending action.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/license-lib.mjs:111