Back to skill

Security audit

Phantra AI: Brand Kit From My Work

Security checks for vulnerabilities and agentic risk

Overview

The skill uses your existing Phantra work to propose visual rules and saves only rules you confirm.

Expect the skill to read your Phantra creative library and project details, then save confirmed rules and create a project. Review the separate phantra-ai-use companion and service permissions. Scanner coverage was partial because of malformed frontmatter; the sole artifact file was independently reviewed, but external tool behavior remains unverified.

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