Security audit
VC LP 报告与知识管理
Security checks across malware telemetry and agentic risk
Overview
This is a focused VC reporting and knowledge-base writing skill that keeps output local by default and requires explicit confirmation before any external publishing.
Before using this skill, users should be careful with confidential LP, fund performance, portfolio, and internal research data. The artifact appropriately defaults to returning Markdown in the chat and requires explicit confirmation before publishing to ima, so users should verify target space, visibility, and desensitization when using that optional publishing path.
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.