Security audit
thinking-jobs-to-be-done
Security checks across malware telemetry and agentic risk
Overview
This is a narrow product-thinking skill that gives Jobs-to-Be-Done analysis guidance without asking for special access or running code.
This skill appears safe to install for product strategy work. Users should still provide only the product documents, tickets, analytics, or notes they intend the agent to analyze, since the skill is designed to reason from supplied evidence.
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.