我的测试节能
Security checks across malware telemetry and agentic risk
Overview
The available evidence shows disclosed, purpose-aligned helper behavior with no artifact-backed malicious or deceptive behavior found.
Use this skill only in workspaces where you are comfortable allowing the agent to run the documented repo and CLI workflows. Keep any GitHub, Convex, OpenAI, or ClawHub tokens scoped to the needed tasks, and review commands carefully before approving actions that publish, moderate, or change account data.
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
63/63 vendors flagged this skill as clean.