Vigil
Security checks across malware telemetry and agentic risk
Overview
This is a disclosed local safety-check wrapper for agent tool calls, with no evidence of hidden execution, data exfiltration, persistence, or destructive behavior in the skill files.
Reasonable to install if you want a local guardrail wrapper for checking proposed agent tool calls. Review and preferably pin the external npm package version, and avoid copying the dangerous examples into any context where they would be executed instead of checked.
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
66/66 vendors flagged this skill as clean.