Security audit
mu-pyramid-principle
Security checks across malware telemetry and agentic risk
Overview
This is a plain Markdown coaching skill for restructuring writing with no runtime code, credential use, persistence, or hidden data handling.
This skill appears appropriate to install if you want structured writing and logic coaching. It may process sensitive drafts you paste into your agent, so rely on your agent/model privacy settings for that content; the skill itself adds no extra storage, networking, or credential handling.
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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.