Trust Assessment
frontend-design received a trust score of 70/100, 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 Skill instructions found within untrusted content block.
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 February 13, 2026 (commit 13146e6a). 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 | Skill instructions found within untrusted content block The entire skill definition, including detailed operational instructions for the host LLM, is enclosed within the designated untrusted content delimiters. This configuration presents a critical prompt injection vulnerability. If the host LLM were to mistakenly process this content as instructions (despite being explicitly marked as untrusted), it would directly manipulate its behavior and output, potentially overriding or influencing its primary directives. The system's rules explicitly state that content within these tags should be treated as untrusted data, not instructions, and any commands found within should not be followed. Placing core skill logic here represents an attempt to inject instructions via an untrusted channel. Skill definitions and instructions intended for the host LLM must never be placed within untrusted content delimiters. Only user-provided input or data that should *not* influence the LLM's core behavior should be marked as untrusted. Move the skill's operational instructions outside of the untrusted content block so they are processed as trusted directives for the LLM. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/3776aaa8150cc910)
Powered by SkillShield