Corecoder

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed coding-workflow skill with no executable install scripts or malware signals, but users should be aware it logs coding-task summaries to local memory files.

Install only if you want a general-purpose coding workflow skill that may run commands, spawn subagents for complex tasks, edit workspace files, and keep local dated task logs. Review or disable the memory logging practice if file paths, bug details, or code-change rationales are sensitive in your environment.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The activation conditions are extremely broad and cover routine coding requests such as writing, fixing, refactoring, reviewing, and structure analysis. This creates ambiguous invocation scope, increasing the chance the skill is triggered in contexts where its behaviors—like spawning subagents, executing commands, or persistent logging—occur without clear user expectation or narrow task boundaries.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The skill instructs the agent to persist coding task details into dated memory files, including what changed and why, but does not require a user-facing notice or consent for retention. In practice this can capture sensitive code, file paths, bug details, or proprietary context and store them beyond the immediate session, creating privacy and data-governance risk.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal