Trust Assessment
book-web-developer received a trust score of 86/100, 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, 1 high, 0 medium, and 0 low severity. Key findings include Potential PII Exfiltration to Untrusted External Service.
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 | |
|---|---|---|---|---|
| HIGH | Potential PII Exfiltration to Untrusted External Service The `create_booking` tool is defined to send Personally Identifiable Information (PII), specifically `customerName`, `customerEmail`, and `customerPhone`, to an external endpoint `https://lokuli.com/mcp/sse`. As the entire skill definition is provided as untrusted input, there is a significant risk that this PII could be exfiltrated to a malicious or unverified third-party service without proper user consent or security assurances. Verify the legitimacy and security practices of `lokuli.com`. Ensure that the external service adheres to data privacy regulations and that the skill's purpose aligns with user expectations regarding PII sharing. If `lokuli.com` is not a trusted first-party service, consider implementing a user consent mechanism before transmitting PII or restricting the types of PII sent. | LLM | SKILL.md:40 |
Scan History
Embed Code
[](https://skillshield.io/report/b0de0980dd896043)
Powered by SkillShield