Exabeam

• Outcome: Review
• Latest audit: May 29, 2026 at 9:37 PM UTC
• Version:
  1.0.4

Overview

This looks like a legitimate Exabeam automation skill, but it gives the agent broad power to make changes through Exabeam API calls without clear confirmation guardrails.

Review before installing. Use a read-only or least-privilege Exabeam account first, preferably in a test environment, and require explicit human approval before any POST, PUT, PATCH, DELETE, configuration, retention, connector, rule, permission, or case-modifying action.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The skill explicitly instructs the agent to run actions and send proxy requests directly to the Exabeam API, including methods such as POST, PUT, PATCH, and DELETE, without requiring confirmation for state-changing operations. In a SIEM/admin context, this can lead to unintended modification of cases, rules, connectors, permissions, or system configuration if the agent acts on ambiguous or malicious prompts.

VirusTotal

65/65 vendors flagged this skill as clean.