Security audit

UE Datatable Editor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Unreal Engine DataTable editor, but it can scan local project folders and make real project-data changes when used.

Install this only if you want an agent to inspect and edit Unreal Engine DataTable JSON files. Prefer giving an explicit project or JSON path, review search results and proposed changes, use dry-run for uncertain edits, keep backups or source control available, and run the UE import command only after confirming the target asset path and validation output.

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (7)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 91% confidence
Finding: The skill instructs the agent to discover project files, read JSON, and modify/write them back, yet it declares no explicit permissions or guardrails. This creates a capability/expectation mismatch where a caller may invoke file-system-affecting behavior without clear consent boundaries, increasing the chance of unintended modification of local project data.

Context-Inappropriate Capability

Medium

Confidence: 91% confidence
Finding: The script's default discovery behavior searches broadly across the current directory, parent directories, the user's home/Desktop/Documents, and on Windows even top-level directories on multiple drives. In an agent skill context, this exceeds the minimum scope needed to operate on a selected Unreal project and can expose unrelated project names, file paths, and DataTable contents, creating unnecessary data overreach and privacy risk.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger phrases are broad enough to match common requests about skills, DataTables, and UE imports without clearly constraining when the skill should activate. In a skill that can auto-discover projects and modify/import configuration data, unintended invocation could cause the agent to inspect local files or guide destructive edits the user did not explicitly intend.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The README advertises automatic discovery, modification, backup, and import behavior but does not prominently warn that these actions can access local project files and alter engine data. Because the skill operates on potentially valuable game configuration assets, insufficient disclosure and confirmation increase the chance of accidental, user-unexpected system and data-impacting actions.

Vague Triggers

Medium

Confidence: 83% confidence
Finding: The trigger language is broad enough to activate on generic references to editing skills, DataTables, or related terms, which can cause the skill to run in contexts where the user did not clearly request project file operations. Because this skill can discover files and change JSON data, over-broad activation raises the risk of unintended invocation followed by sensitive file access or modification.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill explicitly allows direct file editing via tools like replace_in_file and write_to_file, but it does not require a prominent warning or explicit user approval before making persistent changes to project assets. In a development workspace, this can lead to accidental corruption, mass edits, or hard-to-revert changes beyond the intended row or table.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The script imports JSON directly into Unreal Engine DataTables and immediately saves the assets without any confirmation, dry-run, backup, or rollback path. In this skill context, that means a mistaken path, malformed JSON, or unintended invocation can silently overwrite project assets, causing integrity loss and potentially large-scale data corruption in AI skill configuration.

Static analysis

No suspicious patterns detected.