Security audit

Mml

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only MML helper skill with privacy-sensitive examples that users should deploy carefully.

Install is reasonable if you need MML authoring help. Before deploying scenes that use m-position-probe or m-chat-probe, clearly disclose collection to users, limit probe range and retention, avoid exposing raw connection IDs unnecessarily, and handle chat content as user-generated sensitive data.

A.I.G

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

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (4)

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The position-tracking example explicitly demonstrates collecting user location, rotation, and connection identifiers via `m-position-probe` without any privacy notice, consent guidance, or data-minimization warning. In a reusable skill, example code often gets copied directly into production, so this omission can normalize silent user tracking in metaverse environments.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The chat-reactive example shows how to receive `e.detail.message` and `connectionId` from nearby users without any warning that this is user-generated content and identity-linked telemetry. Because the skill is instructional and copy-paste friendly, it increases the chance of deploying chat monitoring features without transparency, consent, or handling guidance for sensitive content.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: This markdown file describes `m-position-probe` as tracking user positions within range and invoking callbacks on enter, move, and leave events. The description documents the behavior technically but does not include any warning about privacy implications or user-data monitoring, which is required for markdown files describing behaviors that could affect user privacy.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The `m-chat-probe` section states that it can receive chat messages from nearby users and trigger `onchat` scripts. This is a privacy-sensitive behavior, but the markdown provides no warning or disclosure about monitoring user communications.

Static analysis

No suspicious patterns detected.