Trust Assessment
web-design-guidelines received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Dynamic Instruction Loading from Untrusted Source.
The analysis covered 4 layers: llm_behavioral_safety, dependency_graph, static_code_analysis, manifest_analysis. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 11, 2026 (commit 0676c56a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Dynamic Instruction Loading from Untrusted Source The skill's core logic, including its 'rules' and 'output format instructions', is dynamically fetched from an external, untrusted URL (`https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md`) before each execution. This allows an attacker who compromises the external repository to inject arbitrary instructions into the LLM, leading to severe prompt injection, potential data exfiltration (by manipulating output format to include sensitive data or send it externally), and possibly command injection if the 'rules' are interpreted as executable code. The skill effectively delegates its behavior to a remote, unverified source, making it highly vulnerable to supply chain attacks. 1. **Embed guidelines:** Integrate the guidelines directly into the skill package or fetch them from a trusted, immutable, and signed source. 2. **Strict parsing:** If dynamic fetching is unavoidable, strictly parse the fetched content for a predefined, safe structure, rather than allowing arbitrary instructions that the LLM might interpret. 3. **Isolate execution:** If 'rules' are programmatic, execute them in a sandboxed environment. 4. **Limit scope:** Ensure fetched content cannot influence the LLM's core instructions or access sensitive system resources beyond the intended scope. | Unknown | SKILL.md:24 |
Scan History
Embed Code
[](https://skillshield.io/report/3e8fdca48476bc33)
Powered by SkillShield