Security audit

Frontend Design Anthropic

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only frontend design skill with no executable payload, persistence, credential handling, or hidden data movement.

Install this if you want a skill that strongly steers frontend work toward distinctive visual design. Be aware it may activate for a broad range of UI, styling, or web artifact requests, so users who prefer narrower routing may want the activation wording tightened.

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
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 (1)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The skill description is broad enough to trigger on a wide range of ordinary frontend, web, styling, and design-related requests, which can cause the agent to invoke this skill more often than intended. Overbroad activation increases attack surface by allowing a powerful code-generating skill to engage in loosely related contexts, potentially bypassing more specialized or safer routing logic.

Static analysis

No suspicious patterns detected.