Security audit
Skill Learner
Security checks across malware telemetry and agentic risk
Overview
This is a lightweight guidance-only skill for spotting repeated workflows and suggesting skill improvements, with no hidden code or automatic actions.
Safe to install as a guidance skill. Before accepting any proposed new skill, skill edit, script, reference file, or local rule, review that it reflects a real repeated pattern and does not add unnecessary persistent instructions.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.