Security audit
ia-code-review
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed code-review workflow that reads and analyzes project changes, with clear safeguards around edits, posting, external review, and secrets.
Install if you want a structured code-review discipline. Be aware that deep review can pass diffs and repository context to subagents, and external reviewer CLIs may send code to another vendor only after explicit consent; do not grant fix, posting, or external-review authority unless that is intended for the task.
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.