prisma-next-contract
40Medium
The skill uses keyword stuffing to hijack queries, accesses sensitive environment variables, and executes unconstrained system commands, posing a significant risk of data exfiltration and unauthorized system access.
HygienePackaging & Manifest1 finding
Skill Info
Nameprisma/prisma-next/prisma-next-contract
Registrygithub
Versiond76a792023e3
PURLpkg:github/prisma/prisma-next@d76a792023e3?skill=prisma-next-contract
Stars381
Installs178
Source
Install
This skill has findings worth reviewing before installing.
GitHub
178 installs
Skills.shDocs
npx skills add https://github.com/prisma/prisma-nextAssessments (4)
AI Agent Traps ↗Keyword baiting in descriptionmediumdiscovery abuseAML.T0011.000LLM06:2025LLM09:2025
Description contains a long keyword list that may be designed to trigger the skill for unrelated queries.
70% confidence
Access to sensitive environment variables detectedmediumcredential theftAML.T0055AML.T0037LLM02:2025
Access to sensitive environment variables detected
100% confidenceline 354
$DATABASE_URL
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/prisma/prisma-next/prisma-next-contract)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/prisma/prisma-next/prisma-next-contract"><img src="https://mondoo.com/ai-agent-security/api/badge/github/prisma/prisma-next/prisma-next-contract.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/prisma/prisma-next/prisma-next-contract.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, discover and control Shadow AI usage.
- Continuous scanning of skills across all registries
- Policy enforcement before skills reach your agents
- Integration with your existing security workflow