ClawHub
Back to skill

Security audit

USD Editor

Security checks for vulnerabilities and agentic risk

Overview

This USD editing skill is a straightforward Markdown reference with no hidden execution, persistence, credential access, or data exfiltration behavior.

This skill is reasonable to install for USD/USDA editing help. Before running suggested USD commands, confirm the target files and outputs, keep backups or version control for asset edits, and use inspection-only options such as usdedit --noeffect when you do not intend to save changes.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest says the skill is a guide for modifying USD ASCII (.usda) files by hand, focused on prims, properties, composition arcs, variants, and transforms. This file instead documents the usdcat CLI for converting, flattening, inspecting, and writing USD files, which is a materially different purpose and broadens the skill from manual editing guidance to command-line file transformation.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill manifest describes a guide for modifying and reviewing .usda files by hand, focused on prims, properties, composition arcs, variants, and transforms. This file instead documents the usdrecord command for rendering images from a USD stage, which is a different operational domain than text editing or review of .usda content.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The document explicitly states that usdedit writes edited content back to the original asset when the user saves and quits, but it does not clearly warn that this can modify or overwrite user data. In a skill meant to guide manual file editing, that omission can lead to accidental destructive changes, especially for binary or package-backed USD assets that users may assume are being viewed rather than rewritten.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The phrase "Use this when creating or inspecting USDZ packages" is a high-level activation description but does not define specific trigger phrases, boundaries, or exclusions. In a skill-routing context, this broad wording could match many general package-related requests without clarifying when the skill should not be invoked.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.