Puppet

Security checks across malware telemetry and agentic risk

Overview

This Puppet skill is coherent and not malicious, but it needs review because it can give an agent broad infrastructure-changing Puppet access without clear confirmation guardrails.

Install only if you trust Membrane and intend to let an agent operate Puppet through that account. Use a least-privileged Puppet/Membrane connection, start in a test or read-only environment, and require explicit human review before jobs, remediation, user or token changes, package or service changes, exec commands, DELETE requests, or other production-impacting actions.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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

Findings (1)

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill explicitly documents raw proxy requests supporting POST, PUT, PATCH, and DELETE without requiring confirmation, authorization checks, or safety guidance for destructive operations. In an infrastructure automation context like Puppet, direct mutating API access can modify configuration, jobs, inventory, or other operational state, making accidental or prompted misuse materially dangerous.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal