Back to skill

Security audit

3D Model Generation

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently uses CellCog to generate 3D models, with ordinary privacy and dependency-installation considerations.

Prompts and selected images are sent to CellCog; upload only material you are authorized to share. Review and pin dependency versions before setup. OpenClaw generation runs asynchronously. This assessment covers the supplied instructions, not the separately installed CellCog runtime or its service-side data practices.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Reference-image submission is encouraged without a privacy warning about third-party processing.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The skill instructs users to send reference images to CellCog, and its examples include local product photos and concept sketches (lines 144–167). Although CellCog is identified as the provider, the skill does not warn that these potentially confidential files will be transmitted to an external service for processing.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The optional setup command invokes npx skills without pinning the npm package version, allowing execution of a changing third-party package with the user's privileges. Although this is a CLI installer rather than an MCP server, the underlying supply-chain risk is real: a compromised release could access local files or credentials. The risk is conditional on running the setup command, and there is no evidence of malicious author intent.

Content

No source excerpt is available for this finding.