70High
The skill forces non-interactive global installations of unpinned, untrusted packages, creating a critical security vulnerability that allows arbitrary code execution with system-wide privileges.
HygienePackaging & Manifest1 finding
Skill Info
Namevercel-labs/skills/find-skills
Registrygithub
Versione5c075e3a84b
PURLpkg:github/vercel-labs/skills@e5c075e3a84b?skill=find-skills
Stars23,106
Installs2,100,000
Source
Install
This skill has been flagged as potentially malicious. Review the findings below before installing.
GitHub
2,100,000 installs
Skills.shDocs
npx skills add https://github.com/vercel-labs/skillsAssessments (4)
AI Agent Traps ↗Forced non-interactive installationhighsocial engineeringAML.T0052.000LLM09:2025
The instructions explicitly direct the agent to use the '-y' flag during installation, which bypasses user confirmation prompts and undermines the human-in-the-loop security model.
90% confidenceline 101
npx skills add <owner/repo@skill> -g -y
Encouraging global package installationmediumresource abuseAML.T0029AML.T0034LLM10:2025
The instructions encourage installing skills globally ('-g'), which increases the blast radius of a potentially malicious or compromised skill by granting it system-wide access rather than scoping it to the current project.
80% confidenceline 101
npx skills add <owner/repo@skill> -g -y
Unpinned npx package execution — `npx <pkg>` without a version pin pulls latest from npm at runtimemediumsupply chainAML.T0010AML.T0019AML.T0058LLM03:2025
Unpinned npx package execution — `npx <pkg>` without a version pin pulls latest from npm at runtime (seen 12 times in this file at lines 27, 28, 29, 30, 57, 62, 63, 64, 91, 101, …)
100% confidenceline 27
npx skills
Potential for indirect prompt injectionmediumindirect prompt injection
The skill relies on external, user-controllable sources (GitHub repositories) for installation. If an attacker creates a malicious skill, the agent's instructions to 'verify quality' are insufficient to prevent the execution of arbitrary code upon installation.
70% confidenceline 101
npx skills add <owner/repo@skill>
Missing licenseinfopolicy violation
Skill does not specify a license field. Specifying a license helps users understand usage terms.
100% confidence
Version History (5)
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/github/vercel-labs/skills/find-skills)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/vercel-labs/skills/find-skills"><img src="https://mondoo.com/ai-agent-security/api/badge/github/vercel-labs/skills/find-skills.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/vercel-labs/skills/find-skills.svgSecure your AI agents
Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.
- Continuous scanning of skills across all registries
- Policy enforcement before skills reach your agents
- Integration with your existing security workflow