Aegis Firewall
Security checks across malware telemetry and agentic risk
Overview
The available evidence does not show artifact-backed malicious or suspicious behavior; the only negative signal is a single VirusTotal engine hit.
Before installing, review the skill page and SKILL.md for the exact instructions it will add to your agent. The lone VirusTotal hit is worth noting, but without supporting artifact evidence it does not justify blocking the skill.
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
1/65 vendors flagged this skill as malicious, and 64/65 flagged it as clean.