AI Agent OPSEC — Runtime Classified Data Enforcer
Security checks across malware telemetry and agentic risk
Overview
This skill is a local redaction helper with disclosed file access and no evidence of hidden network activity or exfiltration.
Install only if you want a local helper for redacting known terms before external calls. Add classified/ and memory/security/ to .gitignore, protect the term registry and audit log, configure external agent names yourself, and use the implemented sanitizeOutbound(...).sanitized value rather than copying outdated examples blindly.
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.