Security audit
投研Skill面试官
Security checks across malware telemetry and agentic risk
Overview
This skill is a structured evaluator for investment-research skills and its file-reading and test-running instructions are disclosed and aligned with that purpose.
Installers should treat this as a benign review aid. When using its actual-verification step, only run target skills you are willing to execute in your agent environment, because any risk would come from the target skill being evaluated rather than this evaluator’s own artifact.
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.