skills-best-practices
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only skill about building and publishing Agent Skills, with no executable payload or hidden runtime behavior found.
Reasonable to install if you want guidance on creating or reviewing Agent Skills. Read it as reference material: it documents sensitive patterns such as credentials, shell commands, and financial capability tags, but the reviewed package itself does not run code or request those powers.
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.