Back to skill

Security audit

PromptLayer

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward PromptLayer connector wrapper with disclosed read-only actions and no hidden behavior found.

Before installing, confirm you trust OOMOL and are comfortable connecting your PromptLayer workspace through its connector. The listed operations read PromptLayer templates, requests, tables, sheets, and rows; review any future connector schema if new write or destructive actions appear.

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

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.