Feature Flags
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only feature-flag planning skill with no executable behavior, credential use, persistence, or hidden system access.
Safe to install as a planning aid. Users should adapt the feature-flag governance advice to their own release process, but the artifact does not show security-relevant access, hidden behavior, or unsafe authority.
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.