Security audit

3D Model Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple French-language guide for using Meshy.ai to create and download 3D models, with no hidden code or persistence.

Install this if you want a French workflow guide for generating 3D models with Meshy.ai. Be aware that using it may send prompts or reference images to Meshy.ai and may require your Meshy account, but the skill itself contains no executable code or hidden persistence.

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

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

Findings (1)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: Le contenu de la compétence est entièrement rédigé en français et ne propose aucune option de langue ou indication d'opt-in pour d'autres locales. Selon la règle SQP-3, forcer une langue spécifique sans choix utilisateur constitue une violation de politique linguistique en langage naturel.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.