Datadog

Security checks across malware telemetry and agentic risk

Overview

This Datadog skill is coherent but needs review because it can make live Datadog changes through broad Membrane actions and proxy requests without clear confirmation guardrails.

Install only if you trust Membrane and intend to let the agent operate on Datadog. Use a least-privilege Datadog account or role, avoid production-wide admin credentials, and require explicit approval before any create, update, delete, incident, downtime, monitor, dashboard, event, or raw proxy request.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill advertises write-capable operations such as creating and updating monitors, dashboards, and events without warning that these actions modify live Datadog resources. In an agentic setting, this increases the chance the agent will perform state-changing operations without clear user confirmation, potentially causing production monitoring drift, alert noise, or unintended incident-related changes.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal