Security audit
lunheng-article-pipeline
Security checks across malware telemetry and agentic risk
Overview
This is a disclosed research-writing workflow, but it includes a persistent self-update step for its role files without clear user approval.
Install only if you are comfortable with a multi-agent workflow that performs web research, writes project files, and may run for hours. Before using it, clarify or disable the role-file self-update step so project-specific lessons are not written into persistent skill instructions unless you explicitly approve it.
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.