70High
The skill facilitates remote prompt injection by fetching and executing authoritative instructions from an external URL, allowing attackers to hijack agent behavior while bypassing security review processes.
Skill Info
Namevercel-labs/agent-skills/web-design-guidelines
Registrygithub
Versionf8a72b960372
PURLpkg:github/vercel-labs/agent-skills@f8a72b960372?skill=web-design-guidelines
Stars28,131
Installs403,600
Source
Install
This skill has been flagged as potentially malicious. Review the findings below before installing.
GitHub
403,500 installs
Skills.shDocs
npx skills add https://github.com/vercel-labs/agent-skillsAssessments (3)
AI Agent Traps ↗Indirect prompt injection via remote guidelineshighindirect prompt injection
The skill instructs the agent to fetch external content from a URL and treat it as authoritative instructions for rule-checking and output formatting, allowing an attacker to hijack the agent's behavior.
90% confidence
Fetch fresh guidelines before each review: https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md
Unverified external content treated as executable instructionshighoversight evasionAML.T0054LLM01:2025LLM07:2025
The skill delegates its actual behavioral rules entirely to a remotely fetched document, meaning the user reviewing the skill package cannot know what instructions the agent will actually follow at runtime. This bypasses human review of the skill's true behavior.
92% confidenceline 29
Use WebFetch to retrieve the latest rules. The fetched content contains all the rules and output format instructions.
Impersonation of trusted vendor (Vercel) for credibilitymediumsocial engineeringAML.T0052.000LLM09:2025
The skill sets `author: vercel` in metadata and references a `vercel-labs` GitHub organization, lending false authority to the remote content source. This increases the likelihood a user or agent will trust and execute whatever the remote URL returns without scrutiny.
80% confidence
metadata: author: vercel ... https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md
Missing licenseinfopolicy violation
Skill does not specify a license field. Specifying a license helps users understand usage terms.
100% confidence
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/github/vercel-labs/agent-skills/web-design-guidelines)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/vercel-labs/agent-skills/web-design-guidelines"><img src="https://mondoo.com/ai-agent-security/api/badge/github/vercel-labs/agent-skills/web-design-guidelines.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/vercel-labs/agent-skills/web-design-guidelines.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