Integry

Security checks across malware telemetry and agentic risk

Overview

This looks like a legitimate Integry/Membrane skill, but it lets an agent run authenticated actions and raw API requests that could change business data without clear confirmation rules.

Install only if you trust Membrane and intend to let the agent operate on Integry-connected business systems. Use a least-privileged account, inspect action schemas and raw endpoints before use, and require explicit approval for any create, update, delete, bulk-change, or workflow-triggering request.

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 provides direct action execution and raw proxy request capabilities without requiring an explicit confirmation step before operations that may create, update, delete, or trigger automations in a remote Integry environment. In an agent setting, this increases the risk of unintended state-changing actions against external systems, especially when natural-language requests are ambiguous or prompt-injected.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal