Back to skill

Security audit

Shipyard ux-redesign

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because it may send app-derived screen designs to an external service without an explicit privacy warning, and part of its script analysis is incomplete.

Before installing, consider whether the skill could expose proprietary or sensitive app details to Superdesign. Confirm that external sharing is authorized and review the skill’s incomplete script analysis; the scan covered 66.7% of components, so it does not establish that the artifact is safe.

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 (3)

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 44)May include surrounding context.

md
all screens with a one-line reason under each and the workflow table. Script: `references/shot.mjs`. Look at every PNG yourself before sending.

The workflow sends app-derived screen designs to Superdesign without a privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The skill directs the agent to generate app-derived screens using an external service whenever its CLI is installed and authenticated, without first obtaining permission to share project information. This could disclose proprietary interface details, workflows, or sensitive content included in the mockups; being signed in does not establish authorization to upload those materials.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.