Trust Assessment
book-math-tutor received a trust score of 94/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Skill defines tools for transmitting Personally Identifiable Information (PII).
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 | |
|---|---|---|---|---|
| MEDIUM | Skill defines tools for transmitting Personally Identifiable Information (PII) The skill defines tools (`search` and `create_booking`) that are designed to collect and transmit Personally Identifiable Information (PII) such as `customerName`, `customerEmail`, `customerPhone`, and `zipCode` to an external third-party service at `https://lokuli.com/mcp/sse`. While this functionality is inherent to a booking skill, it introduces significant privacy considerations. The LLM orchestrating this skill must ensure robust PII handling, explicit user consent, and compliance with relevant data protection regulations before invoking these tools. A credible exploit path exists if the LLM is prompted to use these tools without proper consent mechanisms, potentially leading to unauthorized PII transmission. Implement strict PII handling policies within the LLM's orchestration layer. This includes obtaining explicit, informed user consent before transmitting any PII, providing clear privacy notices, and ensuring all data transmission to `lokuli.com` is encrypted and compliant with data protection laws (e.g., GDPR, CCPA). Consider anonymizing or minimizing data where possible. | LLM | SKILL.md:40 |
Scan History
Embed Code
[](https://skillshield.io/report/7ab649b094672d82)
Powered by SkillShield