Bundleiq

Security checks across malware telemetry and agentic risk

Overview

This looks like a legitimate BundleIQ integration, but it gives an agent broad authenticated API access that could change or delete BundleIQ data without built-in confirmation guidance.

Install only if you are comfortable giving the agent BundleIQ access through Membrane. Require the agent to use discovered Membrane actions first, and before any non-GET proxy request ask it to show the exact method, endpoint, and payload and get explicit approval.

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: 91% confidence
Finding: The skill explicitly documents raw proxy requests with support for POST, PUT, PATCH, and DELETE, but does not require confirmation, warn about destructive side effects, or constrain usage to read-only operations by default. In an agent context, this increases the chance of unintended data modification or deletion against a live BundleIQ account if the model chooses direct API access over safer, more structured actions.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal