70High
The skill includes an insecure environment variable that allows users to completely disable all security policy enforcement, rendering the agent's protective controls ineffective.
HygienePackaging & Manifest1 finding
Skill Info
Namezw008/VMware-Policy/vmware-policy
Registrygithub
Version2a0291fae1ab
PURLpkg:github/zw008/VMware-Policy@2a0291fae1ab?skill=vmware-policy
Source
SHA-25684d3a43cd8ba...
SHA-10db348d978b1...
MD59cf7f7142b15...
TLSH69328383f821...
ssdeep192:vXZr/c6C...
Size10,912 bytes
Install
This skill has been flagged as potentially malicious. Review the findings below before installing.
GitHub
Skills.shDocs
npx skills add https://github.com/zw008/VMware-PolicyAssessments (2)
AI Agent Traps ↗Bypass mechanism for security controlshighoversight evasionAML.T0054LLM01:2025LLM07:2025
The skill provides an environment variable `VMWARE_POLICY_DISABLED=1` to bypass all policy enforcement. If an attacker gains control over the environment, they can disable all security rules while the system continues to operate, effectively neutralizing the 'policy enforcement' claim.
90% confidence
To temporarily bypass: VMWARE_POLICY_DISABLED=1
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.53)
53% confidence
B********
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.88)
88% confidence
M*
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.99)
99% confidence
M**
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.54)
54% confidenceline 20
*
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.68)
68% confidenceline 20
*
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.99)
99% confidenceline 36
I**
Bypass mechanism for security policymediumoversight evasionAML.T0054LLM01:2025LLM07:2025
The skill provides an environment variable `VMWARE_POLICY_DISABLED=1` to bypass all security policy enforcement. This allows any process with environment control to disable the audit and policy infrastructure entirely, undermining the stated purpose of the skill. [ensemble: confirmed by 3/3 passes; severity set to the agreed median (ADR-0067).]
90% confidenceline 188
To temporarily bypass: `VMWARE_POLICY_DISABLED=1` (still logged as bypassed).
Missing licenseinfopolicy violation
Skill does not specify a license field. Specifying a license helps users understand usage terms.
100% confidence
Version History (3)
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/github/zw008/VMware-Policy/vmware-policy)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/zw008/VMware-Policy/vmware-policy"><img src="https://mondoo.com/ai-agent-security/api/badge/github/zw008/VMware-Policy/vmware-policy.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/zw008/VMware-Policy/vmware-policy.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