Agentic Factory

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only software orchestration skill, with broad activation terms and deploy-oriented workflow examples that users should keep under explicit control.

Install this only if you want an assistant to coordinate multi-agent software work. Keep activation intentional, review any spawned sessions, and require explicit approval before repository writes, merges, CI/CD changes, deployments, releases, or production-impacting steps.

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: 89% confidence
Finding: The trigger list is very broad and includes generic terms like "pipeline," "automation," "build system," and "orchestration," which are likely to match ordinary software conversations unrelated to this skill. This can cause the skill to activate unintentionally in contexts involving file changes, CI/CD, or deployment-oriented workflows, expanding the chance of unsafe or overly autonomous behavior being invoked without clear user intent.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The workflow explicitly includes merge, system testing, documentation update, and deploy/release actions, but the skill does not present an explicit warning or confirmation requirement for system-impacting operations. In an agentic orchestration context, omission of such guardrails increases the risk of unintended repository changes or deployment actions being treated as routine automation.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal