OC Code Review

Security checks across malware telemetry and agentic risk

Overview

This is a coherent code-review helper with minor scoping and packaging cautions, not evidence of malicious behavior.

Install this if you want an agent-assisted code review workflow. When invoking it, name the exact files, PRs, repositories, documents, or URLs to review, and avoid granting broad private-code access unnecessarily. Be aware that one referenced performance checklist is missing from the package.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger list includes very broad terms such as "review" and "审查", which can cause the skill to activate in contexts far beyond code review. In an agent environment, overbroad invocation can redirect unrelated user tasks into tool-using review flows, increasing the chance of unnecessary file access, command execution, or confusing behavior.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal