Security audit
稽影 · 多Agent信任基础设施
Security checks across malware telemetry and agentic risk
Overview
This skill is a short informational description of a trust-infrastructure project and does not request sensitive access or run commands.
This appears safe to install as an informational skill, but it mainly links to and describes an external project. Review the linked repository separately before running any project code, connecting APIs, or providing credentials.
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.
Static analysis
No suspicious patterns detected.