Security audit
mao-methodology
Security checks across malware telemetry and agentic risk
Overview
This skill is a methodology/reference package with templates and one optional local document parser, with no evidence of hidden access, persistence, or data exfiltration.
Install this if you want Mao-methodology reference material and analysis templates. Only run the helper script on documents you intend to process, install python-docx from a trusted source if needed, and review the political/adversarial strategy framing for fit with your intended use.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.