continuous-agent-loop
Security checks across malware telemetry and agentic risk
Overview
This skill provides disclosed autonomous-loop guidance and a local repository audit script without hidden network access, writes, or persistence.
Install this if you want autonomous-agent loop guidance and a local repository audit helper. Run the audit only against the intended project using AUDIT_ROOT or --root, and keep human approval around any workflow that would push, open PRs, or merge code.
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
65/65 vendors flagged this skill as clean.