Prisma

Security checks across malware telemetry and agentic risk

Overview

This skill is a legitimate Membrane-based 0codekit integration, but it gives the agent broad authenticated action and raw API request capability without clear safeguards for write or delete operations.

Install only if you trust Membrane and intend the agent to operate on your 0codekit account. Prefer read-only action discovery first, confirm every create/update/delete or raw proxy request, and avoid connecting production or sensitive workspaces unless the requested operation is specific and reversible.

SkillSpector

By NVIDIA

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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)

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill explicitly instructs the agent to run actions and arbitrary proxy requests against a live Prisma-connected backend without requiring confirmation or warning that these operations may create, update, or delete remote data. In an agent setting, this can lead to unintended destructive changes to production databases, especially because direct request capability broadens access beyond safer prebuilt actions.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal