Looker

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Looker integration that uses Membrane for authenticated access, with normal third-party integration risks but no evidence of hidden or malicious behavior.

Install only if you trust Membrane and the @membranehq CLI. Use a least-privileged Looker account, review the Membrane connection permissions, and require explicit confirmation before actions that change or delete Looker resources.

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: 84% confidence
Finding: The skill description is broad enough to match many generic 'data' or 'records' requests, which can cause the agent to invoke this integration outside the user's intended system. In a network-enabled skill that can create connections and issue API/proxy requests, over-broad routing increases the chance of unintended external actions or data exposure.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal