Back to skill

Security audit

Viking Memory System Ultra

Security checks for vulnerabilities and agentic risk

Overview

The skill is a persistent agent memory system, but it directs cross-agent sharing and external LLM processing of archived memories without clear privacy controls.

Review before installing. Use it only if you are comfortable with persistent agent memories, cross-agent visibility for shared memories, and possible external LLM processing of archived memory content. Do not store secrets, credentials, private personal data, or sensitive business decisions unless the underlying scripts provide explicit approval, redaction, and local-only controls.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly instructs syncing 'important memories' into a shared global memory space visible to other agents, but it does not prominently warn that the content becomes cross-agent accessible. This creates a confidentiality risk because users or downstream agents may store sensitive decisions, notes, or operational details under the assumption they remain local.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill describes automatic LLM-based semantic scanning of cold/archive memories and sending task context to external model providers, but it does not provide a clear privacy notice or data-handling boundary. Archived memories may contain sensitive historical content, so automatic scanning and API submission can expose data to third-party services or broaden internal data access without informed consent.

Content

No source excerpt is available for this finding.