Delegation
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only coding workflow skill that asks an agent to follow project architecture before writing code, with no hidden execution, data access, persistence, or credential handling.
This skill appears safe to install as a workflow aid. Users should provide an accurate architecture document because the skill tells the agent to treat that document as the main source of truth for code decisions.
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
62/62 vendors flagged this skill as clean.