Security audit
AI行业新闻搜集小技能
Security checks across malware telemetry and agentic risk
Overview
This skill only tells an agent to gather and summarize AI industry news from web sources for a user-specified time range and topic.
Before installing, understand that the skill will use web sources to summarize AI news, so answer quality depends on source reliability and recency. There is no artifact evidence of unsafe behavior beyond ordinary web research.
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.
Static analysis
No suspicious patterns detected.