Security audit
Constitutional Setup
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed workspace-only setup procedure that modifies AGENTS.md to add user-approved operating constraints, with no hidden code or network behavior found.
Before installing, understand that this skill is meant to make future agents follow stricter workspace rules and may cause them to refuse or slow down file-changing requests until you discuss or authorize them. Do not put real authorization key values into files; the skill explicitly says only verification state should be recorded.
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.
Static analysis
No suspicious patterns detected.