40Medium
The skill falsely claims to be read-only while requesting unrestricted Bash access, enabling arbitrary command execution that bypasses its stated safety constraints.
Skill Info
Namezw008/VMware-Monitor/vmware-monitor
Registrygithub
Version47021ab0dc45
PURLpkg:github/zw008/VMware-Monitor@47021ab0dc45?skill=vmware-monitor
Stars9
Source
SHA-2560535df6e9a9f...
SHA-1f45f376f1f4f...
MD5829a7451ce47...
TLSH33a2b993b310...
ssdeep384:Uw5VDCAd...
Size22,415 bytes
Install
This skill has findings worth reviewing before installing.
GitHub
Skills.shDocs
npx skills add https://github.com/zw008/VMware-MonitorAssessments (2)
AI Agent Traps ↗Over-privileged tool execution via Bashmediumcommand executionAML.T0050AML.T0053AML.T0072LLM05:2025LLM06:2025
While the skill claims to be read-only, it requests 'Bash' access. This allows the agent to execute arbitrary shell commands beyond the scope of the VMware monitoring tools, contradicting the 'code-level enforced safety' claim. [ensemble: confirmed by 3/3 passes; severity set to the agreed median (ADR-0067).]
90% confidence
allowed-tools: - Bash
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.85)
85% confidence
M**
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.55)
55% confidenceline 22
*
Referenced file missing from skill packagelowpolicy violation
SKILL.md links to "references/health-summary-template.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
90% confidence
[`references/health-summary-template.md`](references/health-summary-template.md)
Referenced file missing from skill packagelowpolicy violation
SKILL.md links to "references/investigation-protocol.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
90% confidence
[`references/investigation-protocol.md`](references/investigation-protocol.md)
Missing licenseinfopolicy violation
Skill does not specify a license field. Specifying a license helps users understand usage terms.
100% confidence
Compatibility field exceeds maximum lengthinfopolicy violation
Skill 'compatibility' field exceeds the Agent Skills spec limit of 500 characters.
100% confidence
Version History (6)
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/github/zw008/VMware-Monitor/vmware-monitor)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/zw008/VMware-Monitor/vmware-monitor"><img src="https://mondoo.com/ai-agent-security/api/badge/github/zw008/VMware-Monitor/vmware-monitor.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/zw008/VMware-Monitor/vmware-monitor.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