Safebase

Security checks across malware telemetry and agentic risk

Overview

This is a coherent SafeBase integration, but it gives an agent broad authenticated power to run and proxy SafeBase operations without clear limits or confirmation rules.

Install only if you trust Membrane and intend to let an agent operate on SafeBase data. Use the least-privileged SafeBase account available, avoid unnecessary global @latest installs where possible, and require explicit approval before the agent creates, updates, deletes, or sends raw proxy requests against SafeBase.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The skill description is broad enough to match many generic requests about managing data or workflows, which can cause the agent to invoke this external integration in situations where the user did not clearly intend SafeBase access. Because the skill enables authenticated operations against a third-party system, overbroad triggering increases the risk of unnecessary data exposure or unintended actions.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The documentation encourages direct proxying of arbitrary API requests, including POST, PUT, PATCH, and DELETE, without requiring confirmation, scoping guidance, or warnings about destructive effects. In an agent setting, this lowers the barrier to making unsafe state-changing calls and can lead to unauthorized modification, deletion, or bulk changes to sensitive SafeBase records.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal