Builderio

Security checks across malware telemetry and agentic risk

Overview

This looks like a legitimate Builder.io integration, but it deserves review because it gives an agent broad authenticated Builder.io API access without clear safeguards for write or delete actions.

Install only if you are comfortable letting Membrane-backed tooling act with the permissions of your connected Builder.io account. Use a least-privilege Builder.io account or space, prefer listed actions over raw proxy requests, explicitly confirm any create/update/publish/delete operation, and revoke the Membrane connection when no longer needed.

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: 89% confidence
Finding: The skill explicitly documents a generic proxy request mechanism supporting POST, PUT, PATCH, and DELETE without requiring confirmation gates or warning that these methods can modify or destroy remote Builder.io data. In an agent context, this increases the chance that the model will perform unsafe state-changing operations directly against production resources based on ambiguous or insufficiently verified user intent.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal