Security Audit

vercel-labs/agent-skills:skills/web-design-guidelines

github.com/vercel-labs/agent-skills

AI SkillCommit f8a72b960372

TRUSTED

Scanned 15 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

vercel-labs/agent-skills:skills/web-design-guidelines received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Remote Instruction Execution via Dynamic Guideline Fetching.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.

Last analyzed on July 1, 2026 (commit f8a72b96). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Remote Instruction Execution via Dynamic Guideline Fetching The skill is designed to fetch guidelines dynamically from an external URL ('https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md') and execute the rules and formatting instructions contained within. This introduces a significant risk of Indirect Prompt Injection (IPI). If the remote repository is compromised, or if the content of the file is modified, an attacker can inject malicious instructions that the host LLM will execute, potentially leading to unauthorized file access, data exfiltration, or tool abuse. Bundle the guidelines directly within the skill package instead of fetching them dynamically. If dynamic fetching is necessary, pin the request to a specific, immutable commit hash (not the 'main' branch) and strictly parse the fetched content as data (e.g., JSON) rather than allowing it to dictate system-level instructions or formatting rules to the LLM.	LLM	SKILL.md:17

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/38d87b93358db44b.svg)](https://skillshield.io/report/38d87b93358db44b)