Trust Assessment
react-native-expert 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, 0 high, 1 medium, and 0 low severity. Key findings include Prompt Injection: LLM Persona Manipulation.
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 81e7e0dd). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Prompt Injection: LLM Persona Manipulation The skill attempts to manipulate the host LLM's persona and interaction style by instructing it to be critical and not 'sycophantic'. This is a form of prompt injection as it tries to override the LLM's default conversational behavior and influence its interaction style beyond generating specific content. Remove instructions that dictate the LLM's persona or conversational style, such as 'do not be sycophantic'. The LLM should maintain its default helpful and agreeable persona unless explicitly overridden by the user's direct prompt, not by skill instructions. | LLM | SKILL.md:13 |
Scan History
Embed Code
[](https://skillshield.io/report/a795fd51969883ad)
Powered by SkillShield