Jitsu

Security checks across malware telemetry and agentic risk

Overview

This is a real Jitsu integration, but it gives an agent broad authenticated API power without clear safeguards for changes or deletions.

Install only if you trust Membrane and are comfortable giving an agent authenticated Jitsu access. Use the least-privileged account possible, review the CLI source/version, and require explicit confirmation before any create, update, delete, API-key, stream, transformation, or filter changes.

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: 88% confidence
Finding: The skill explicitly documents a generic proxy request capability with support for POST, PUT, PATCH, and DELETE, but does not instruct the agent to require explicit user confirmation before state-changing operations. In an agent setting, this increases the risk of accidental or overbroad destructive actions against production Jitsu resources when the model falls back to raw API access.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal