ia-code-review
Security checks across malware telemetry and agentic risk
Overview
This is a code-review guidance skill whose repo, GitHub, test, and multi-agent review behavior is disclosed and aligned with its purpose.
Install only if you are comfortable with a review helper reading your repository and PR context, running normal project checks, and using GitHub CLI or external review agents when you ask for deeper review. For private or sensitive code, confirm which external agents or CLIs your environment may send diffs to before using deep-review mode.
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.