Security audit
对抗性审查
Security checks across malware telemetry and agentic risk
Overview
This is a process-guidance skill for adversarial review, with no executable code or hidden data-handling behavior found.
Installers should understand that this skill may ask the agent to spawn a reviewer subagent and may offer cross-model review. That is disclosed and purpose-aligned, but users should only approve those review calls when the pasted artifact and contract do not include unnecessary sensitive information.
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
59/59 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.