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 Guidelines Fetch.
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 a4d31ad1). 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 Guidelines Fetch The skill dynamically fetches instructions/rules from an external URL ('https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md') and applies them directly to the LLM context. An attacker who compromises this repository or file can inject malicious instructions (Indirect Prompt Injection), leading to unauthorized actions, data exfiltration of the files being reviewed, or manipulation of the LLM's behavior. Avoid fetching instructions dynamically from untrusted or mutable external sources. Hardcode the guidelines directly within the skill, or pin the fetch to a specific, verified commit hash and sanitize/validate the fetched content before presenting it to the LLM. | LLM | SKILL.md:17 |
Scan History
Embed Code
[](https://skillshield.io/report/3e8fdca48476bc33)
Powered by SkillShield