Security audit
Weekly Report Skill-周报生成
Security checks across malware telemetry and agentic risk
Overview
The supplied scan evidence shows no malware detections or agent-risk findings, and there is no artifact-backed reason to hold this skill for review.
This skill can be installed under the normal trust model for community skills. As with any skill, review its visible instructions before use and be cautious if a future version asks for credentials, broad filesystem access, persistent background behavior, or permission to make irreversible changes.
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
48/48 vendors flagged this skill as clean.