Security audit
shared-patterns
Security checks across malware telemetry and agentic risk
Overview
This skill is a documentation-only collection of reusable development patterns and does not request unusual access or perform hidden actions.
This appears safe to install as a documentation helper. Users should still treat its shell and Python snippets as examples to review before running in their own repositories, especially commands that modify packages or files.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.