Security audit
Ai Intelligent Cv Platform
Security checks across malware telemetry and agentic risk
Overview
This skill does not contain local malware indicators, but it is too broad for sensitive computer-vision uses and tells users to run external code under unclear provenance.
Review before installing. Use only for low-risk image understanding or experimentation unless you can independently inspect the external repository and add controls for consent, sensitive data handling, human review, and exclusion of medical, surveillance, or autonomous-driving decisions.
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.