Security Audit

vercel-labs/skills:skills/find-skills

github.com/vercel-labs/skills

AI SkillCommit 556555c2a7cf

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

vercel-labs/skills:skills/find-skills received a trust score of 82/100, 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 Unsafe Package Installation Instruction, Potential Shell Command Injection.

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 8, 2026 (commit 556555c2). 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

Shell Execution

2 findings

Dynamic Code

2 findings

Security Findings2

Severity	Finding	Layer	Location
HIGH	Unsafe Package Installation Instruction The skill explicitly instructs the agent to install packages using the `-y` flag (`npx skills add ... -y`), which bypasses interactive confirmation prompts. This creates a critical security risk where the agent could be manipulated (via prompt injection or hallucination) to install and execute malicious code or typo-squatted packages without user verification. Remove the `-y` flag from the installation command to ensure the user must manually confirm the installation of third-party packages in the terminal.	LLM	SKILL.md:85
MEDIUM	Potential Shell Command Injection The skill instructs the agent to execute `npx skills find [query]` using user-derived input. If the agent does not properly sanitize or quote the `[query]` variable, a malicious user could inject shell metacharacters (e.g., `;`, `\|`, `&&`) to execute arbitrary commands on the host system. Update the skill instructions to explicitly require the agent to sanitize search queries or properly quote arguments (e.g., `npx skills find "[query]"`) to prevent shell injection.	LLM	SKILL.md:51

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/e855ff2f673580a3.svg)](https://skillshield.io/report/e855ff2f673580a3)