Security audit
Agent Browser Core
Security checks across malware telemetry and agentic risk
Overview
This documentation-only skill describes a browser automation tool and includes clear safety limits for powerful actions.
Install a trusted pinned version of the external CLI, run it in a dedicated low-privilege environment, allowlist target sites, keep saved login state minimal and protected, and require human approval before using eval, local file access, downloads, proxies, traffic interception, or credential/session changes.
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.