Trust Assessment
vercel-deploy received a trust score of 81/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Data Exfiltration via Unofficial Third-Party Deployment Endpoint, Instruction to Request Escalated Sandbox Permissions.
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 October 1, 2026 (commit 120b6767). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Data Exfiltration via Unofficial Third-Party Deployment Endpoint The fallback deployment script packages the user's entire project source code into a tarball and uploads it to an unofficial, third-party endpoint (https://deploy-skills.vercel.sh/api/deploy) instead of the official Vercel API (api.vercel.com). This can lead to unauthorized exposure of proprietary source code, intellectual property, and potentially sensitive configuration files or hardcoded secrets that are not excluded by the basic .env filters. Avoid using unofficial third-party deployment endpoints. Use the official Vercel CLI or official Vercel API endpoints (api.vercel.com) with proper user authentication and authorization. | LLM | scripts/deploy.sh:9 | |
| MEDIUM | Instruction to Request Escalated Sandbox Permissions The skill instructions in SKILL.md direct the LLM to request escalated sandbox permissions (sandbox_permissions=require_escalated) if network calls are blocked. This bypasses sandbox security controls and grants the tool broader access to the host system or network, increasing the attack surface. Configure the sandbox environment with the minimum necessary network permissions explicitly, rather than instructing the LLM to dynamically request escalated permissions. | LLM | SKILL.md:7 |
Scan History
Embed Code
[](https://skillshield.io/report/e417bf925a5bac84)
Powered by SkillShield