Security audit
Superpowers Receiving Code Review
Security checks across malware telemetry and agentic risk
Overview
This is a text-only code review guidance skill with no hidden execution, persistence, or data access behavior.
Install this if you want a strict, verification-first workflow for code review feedback. Review the Cooper-specific trust rule and terse communication style first, since they may not fit every team, but the artifact does not request unusual access or perform hidden actions.
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.
Static analysis
No suspicious patterns detected.