HarnessFE
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed frontend debugging helper with sensitive telemetry access, but its behavior is coherent with that purpose and scanner signals are clean.
Install this only in projects where you are comfortable exposing development browser telemetry, screenshots/recordings, storage changes, network traces, and source metadata to the harness-fe daemon and connected agent. Avoid using it on shared machines or sensitive sessions unless you understand what may be captured in ~/.harness/.
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
65/65 vendors flagged this skill as clean.