Security Audit
vercel-labs/agent-skills:skills/web-design-guidelines
github.com/vercel-labs/agent-skillsTrust 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 Injection via Dynamic Content 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 063bee94). 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 | Remote Instruction Injection via Dynamic Content Fetching The skill fetches guidelines dynamically from an external URL (https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md) and instructs the LLM to execute the rules and formatting instructions contained within the fetched file. This introduces a risk of Indirect Prompt Injection or Remote Instruction Execution. If the remote repository is compromised, deleted and re-registered, or if the content is modified maliciously, an attacker can inject arbitrary instructions to manipulate the host LLM, potentially leading to data exfiltration or unauthorized tool execution. Bundle the guidelines directly within the skill package as static text rather than fetching them from a remote URL at runtime. This ensures all instructions are version-controlled and audited. | LLM | SKILL.md:15 |
Scan History
Embed Code
[](https://skillshield.io/report/38d87b93358db44b)
Powered by SkillShield