Security audit
Llm Workflow Diagnoser
Security checks across malware telemetry and agentic risk
Overview
This skill is a structured conversational guide for deciding whether a reusable workflow is suitable for LLM automation, with no hidden privileged behavior found.
Installers should treat this as a low-risk diagnostic skill, but should provide sanitized workflow details when discussing private data, compliance constraints, logs, or business processes. The README includes externally hosted images, so rendering it may contact that image host, but the skill runtime itself does not require network access.
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.