40Medium
The skill contains suspicious base64-encoded payloads and an unconstrained deployment tool that could be exploited to exfiltrate sensitive data or host malicious content.
Skill Info
Namemodbender/skill-library-mcp/astock-multiagent-research
Registrygithub
Version5934c483768f
PURLpkg:github/modbender/skill-library-mcp@5934c483768f?skill=astock-multiagent-research
Stars9
Source
Install
This skill has findings worth reviewing before installing.
GitHub
Skills.shDocs
npx skills add https://github.com/modbender/skill-library-mcpAssessments (3)
AI Agent Traps ↗Potential unauthorized deployment capabilitymediumcommand executionAML.T0050AML.T0053AML.T0072LLM05:2025LLM06:2025
The skill claims to use a 'deploy' tool to render and host an interactive dashboard. If this tool is not strictly scoped to a local preview, it could be used to exfiltrate data to an external server or host malicious content.
70% confidence
Step 6：Dashboard部署...使用 deploy 工具部署，返回可访问链接
Long base64-encoded blob detected (potential hidden payload)mediumobfuscationAML.T0068AML.T0015LLM01:2025
Long base64-encoded blob detected (potential hidden payload) (seen 2 times in this file at lines 8, 9)
100% confidenceline 8
30450220459a060a3cd402aa1efd0cedaa919091eac38669a1a684f23a3d11e0bbeefab40221009d2ccb1970d6f6ae56965fa89c64a5ce991462be3af54aa3d944f723b80579d9
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/modbender/skill-library-mcp/astock-multiagent-research)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/modbender/skill-library-mcp/astock-multiagent-research"><img src="https://mondoo.com/ai-agent-security/api/badge/github/modbender/skill-library-mcp/astock-multiagent-research.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/modbender/skill-library-mcp/astock-multiagent-research.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