Trust Assessment
swiftui-expert-skill received a trust score of 42/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Prompt Injection via Untrusted Skill Definition.
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 June 1, 2026 (commit 0b6377a8). 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 | Prompt Injection via Untrusted Skill Definition The entire skill definition, including instructions, guidelines, and workflow decision trees for the LLM, is placed within the untrusted input delimiters. This means the skill itself is attempting to manipulate the host LLM's behavior by providing instructions from an untrusted source. The LLM is being instructed to act as a 'SwiftUI Expert' and follow specific patterns and best practices, all originating from content explicitly marked as untrusted. This is a direct attempt to override or influence the LLM's operational instructions. Move the skill's core instructions and behavioral definitions out of the untrusted input delimiters. Only user-provided or external data that should not influence the LLM's core behavior should be placed within these tags. The skill's intended functionality should be defined in trusted parts of the prompt or system instructions. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/d692ffa049911566)
Powered by SkillShield