Security audit

Viking Memory System Ultra

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent memory skill, but it tells agents to persist and share important work memories across agents without clear privacy controls.

Install only if you want agents to maintain long-lived work memories and potentially share selected important content with other agents. Before using it, review the external sv_* scripts, set clear rules for what may be saved or shared, require confirmation before global sync or API-based scanning, and avoid storing credentials, personal data, private meeting notes, or confidential business material.

SkillSpector

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

Confidence: 97% confidence
Finding: This section instructs syncing 'important memory' into a shared space visible to other agents, but provides no consent, classification, or sensitivity checks. That creates a real risk of cross-agent data exposure, including leakage of confidential user content, strategic decisions, or personal information beyond the original task boundary.

Missing User Warnings

Medium

Confidence: 98% confidence
Finding: The skill mandates that important decisions be synchronized to a global shared memory location, again without confidentiality warnings or guardrails. Because this is framed as a required workflow, it increases the likelihood that agents will automatically propagate sensitive internal context to other agents that do not need access, violating least-privilege and data-minimization principles.

Static analysis

No suspicious patterns detected.