DeepSeek Brand Guidelines
Security checks across malware telemetry and agentic risk
Overview
This is a guidance-only coding methodology skill with no executable code, credential handling, network behavior, or hidden high-impact actions.
This skill appears safe to install if you want a coding workflow aid. It will influence how an agent approaches code changes and reviews, but the reviewed artifacts are plain instructional text with no executable behavior or sensitive access requests.
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.