Forgerock

• Outcome: Review
• Latest audit: May 29, 2026 at 9:36 PM UTC
• Version:
  1.0.2

Overview

This ForgeRock skill is transparent about using Membrane, but it gives an agent broad authenticated IAM access, including write and delete API calls, without clear approval guardrails.

Review before installing. Use this only if you trust Membrane and are comfortable routing ForgeRock administration through it. Connect a least-privileged ForgeRock account, prefer documented Membrane actions over raw proxy calls, and require explicit user approval before any create, update, delete, group, user, or access-control change.

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: 91% confidence
• Finding: The skill explicitly documents a generic proxy capability that can issue arbitrary HTTP methods, headers, query parameters, and bodies against the ForgeRock API, but it provides no warning or guardrails around destructive operations. In an identity and access management context, this can enable unintended modification or deletion of users, groups, attributes, or access settings if an agent uses the proxy naively or under prompt manipulation.

VirusTotal

65/65 vendors flagged this skill as clean.