Trust Assessment
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 Indirect Prompt Injection via External Resource 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 October 1, 2026 (commit 439cd3a9). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Indirect Prompt Injection via External Resource Fetching The skill is designed to dynamically fetch guidelines from an external URL (https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md) and execute/apply them as instructions ('The fetched content contains all the rules and output format instructions'). This exposes the LLM to Indirect Prompt Injection (IPI). If the external repository is compromised or the file is modified, an attacker can inject malicious instructions that the LLM will execute, potentially leading to unauthorized tool use, data exfiltration, or credential harvesting. Hardcode the guidelines directly within the skill package, or if dynamic fetching is necessary, pin the URL to a specific immutable commit hash (not 'main') and strictly parse the fetched content as data (e.g., JSON) rather than allowing it to dictate system instructions or output formats. | LLM | SKILL.md:13 |
Scan History
Embed Code
[](https://skillshield.io/report/3e8fdca48476bc33)
Powered by SkillShield