Back to skill

Security audit

luma

Security checks for vulnerabilities and agentic risk

Overview

This skill only documents how to check existing retired Luma task status through RunAPI and does not include hidden scripts or broad local access.

Install this only if you intend to use RunAPI for existing Luma task status checks and are comfortable installing the runapi CLI from its Homebrew tap. Use environment or saved CLI authentication carefully, and do not use the skill to create new Luma tasks because the model is retired.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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