Security audit
Subagent Prompt
Security checks across malware telemetry and agentic risk
Overview
The available scan evidence is clean and does not show artifact-backed signs of unsafe behavior.
This skill has clean VirusTotal and SkillSpector results in the supplied context, with no concrete artifact evidence of malicious or suspicious behavior. Because full artifact contents were not available in the workspace for deeper validation, install it with the normal caution you would apply to any skill: review its displayed instructions and avoid granting credentials or broad local access unless those permissions clearly match your intended use.
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.