Security audit
faq-knowledge-mining
Security checks across malware telemetry and agentic risk
Overview
This skill coherently turns user-provided, desensitized customer-service logs into FAQ Markdown without hidden network, credential, or persistence behavior.
Before installing, use this only with logs that have already been stripped of customer private data. The skill will read the supplied file contents to generate FAQs, and generated FAQ output should be reviewed by a business expert before importing into a knowledge base.
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.