Back to skill

Security audit

UE5 Blueprint Automation

Security checks for vulnerabilities and agentic risk

Overview

The skill provides coherent, permission-based Unreal Engine automation instructions, with limited installation and troubleshooting risks.

Review the separately downloaded runtime before running its installer; this verdict covers the bundled documentation. Keep the bridge local and its token private. Back up project assets because ordinary undo does not restore deleted assets. If applying the build-settings workaround, preserve and restore the original files and avoid concurrent builds that depend on them.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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 (2)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 399)May include surrounding context.

md
- 端到端示例:`references/EXAMPLES.md`

Instructions to move user-wide build configurations omit a warning about effects on other projects and restoring the files.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The troubleshooting advice directs an agent to move user-wide build configuration files, potentially changing toolchain selection and build behavior for unrelated Unreal projects. Although it explicitly describes the move as temporary and has a legitimate compatibility purpose, it provides no restoration procedure or warning about concurrent builds; this creates a limited operational safety risk rather than evidence of malicious activity or credential exposure.

Content

No source excerpt is available for this finding.