Design Red Team Audit
Security checks across malware telemetry and agentic risk
Overview
This is a text-only design critique skill that stays within its stated purpose and does not request system access or sensitive permissions.
Safe to install from a security perspective. The practical consideration is content sensitivity: only provide design docs, pitches, metrics, or proprietary plans that you are comfortable having the model analyze, and give clear constraints if the critique should avoid certain assumptions.
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
66/66 vendors flagged this skill as clean.