日报/周报生成器
Security checks across malware telemetry and agentic risk
Overview
This skill formats user-provided work items into daily or weekly reports and shows no hidden data access, network use, persistence, or unsafe automation.
Safe to install based on the supplied artifacts. Use generated reports as drafts, especially military-format output: verify quality record numbers, review IDs, and standards citations before official submission, and avoid entering classified or protected work details unless your agent environment is approved for that 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
64/64 vendors flagged this skill as clean.