德胧调研报告技能
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only research report assistant with no code execution, credential use, persistence, or hidden behavior found.
This skill appears safe to install for research-report drafting. Users should still verify market data and citations it produces, and avoid sharing confidential business information unless they trust the agent environment and any research tools being used.
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.