Security Audit

vercel

github.com/Mrc220/agent_flywheel_clawdbot_skills_and_integrations

AI SkillCommit c7bd8e0f6900

TRUSTED

Scanned 9 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

vercel 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 Skill grants broad Vercel account control, `vercel env pull` command can lead to environment variable exfiltration.

The analysis covered 4 layers: manifest_analysis, llm_behavioral_safety, dependency_graph, static_code_analysis. All layers scored 70 or above, reflecting consistent security practices.

Last analyzed on February 11, 2026 (commit c7bd8e0f). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

78%

Behavioral Risk Signals

Filesystem Write

1 finding

Shell Execution

2 findings

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Skill grants broad Vercel account control The skill documents and implicitly enables access to a wide range of Vercel CLI commands, including those for deleting projects (`vercel project rm`), adding domains (`vercel domains add`), and managing environment variables (`vercel env add/rm`). If an agent is granted access to this skill, it effectively gains full control over the associated Vercel account, allowing for destructive actions, resource manipulation, and potential service disruption. This represents a significant security risk if the agent's access is not strictly controlled. Implement granular access control for the Vercel CLI token used by the agent, or restrict the specific Vercel commands the agent is allowed to execute. Consider using a dedicated Vercel project/account with minimal necessary permissions for agent operations. Ensure that user input for commands like project names or domain names is thoroughly sanitized to prevent command injection.	Unknown	SKILL.md:40
MEDIUM	`vercel env pull` command can lead to environment variable exfiltration The skill documents the `vercel env pull` command, which writes all environment variables for a project to a local `.env` file. If an agent executes this command and subsequently has file system read capabilities, it could read and exfiltrate sensitive environment variables (e.g., API keys, database credentials) stored in the `.env` file. This creates a direct path for data exfiltration. Restrict the agent's ability to execute `vercel env pull`. If this command is necessary, ensure that the agent's execution environment does not allow reading or transmitting local files, especially `.env` files. Implement strict output filtering for any commands that might expose sensitive data.	Unknown	SKILL.md:68

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/23bfb7b027ac0383.svg)](https://skillshield.io/report/23bfb7b027ac0383)