stata-skill

Security checks across malware telemetry and agentic risk

Overview

This skill transparently helps an agent run Stata workflows, with powerful but expected abilities like executing do-files and installing Stata packages.

Install this only if you want an agent to automate Stata. Review do-files before execution, approve ado package names and sources before installation, and remember that Stata logs and analyzed datasets may contain sensitive data.

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: 89% confidence
Finding: The description includes a broad catch-all trigger ('Other actions if you need to use Stata') in addition to many common Stata tasks, which can cause the skill to activate for a wide range of ordinary requests. Over-broad activation increases the chance an agent invokes code-execution or package-installation capabilities unnecessarily, expanding attack surface and creating opportunities for unsafe tool use on untrusted inputs.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal