Adversarial Robustness Toolbox
Security checks across malware telemetry and agentic risk
Overview
This skill is a static reference helper that only prints documentation text and shows no evidence of credential access, network use, persistence, or system changes.
This appears safe to install as a low-privilege reference skill. Treat the technical content as generic guidance rather than authoritative documentation, and verify details against the real Adversarial Robustness Toolbox docs before relying on it for security or engineering 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
66/66 vendors flagged this skill as clean.