ClawHub

Stormboard

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate Stormboard integration, but it gives an agent broad authenticated Stormboard access without clear limits or approval steps for risky changes.

Install only if you trust Membrane and are comfortable giving an agent access to your Stormboard account. Use a least-privileged account where possible, review the Stormboard/Membrane authorization prompts, and require explicit user confirmation before any create, update, delete, or raw proxy request.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Description-Behavior Mismatch

Medium
Confidence
91% confidence
Finding
The manifest and description frame the skill as managing organizations, but the body of the skill authorizes broad interaction with Stormboard data and generic API access. This scope mismatch can cause an agent or reviewer to underestimate the skill's capabilities, increasing the chance of overbroad use and unintended access to non-organization resources.

Context-Inappropriate Capability

Medium
Confidence
95% confidence
Finding
The proxy-request section permits arbitrary requests to Stormboard endpoints, including any path and HTTP method, which materially exceeds a narrow organization-management use case. In an agent setting, this creates a generic authenticated request primitive that can be used to read, modify, or delete unrelated tenant data if invoked improperly or via prompt-driven misuse.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The invocation text is broad enough that the skill may be selected for many requests involving Stormboard, not just organization management. Overbroad routing increases the likelihood that an agent will invoke a skill with powerful authenticated capabilities in contexts where a narrower or read-only tool should have been used.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The documentation presents direct API requests with destructive methods such as POST, PUT, PATCH, and DELETE without emphasizing approval requirements, safety checks, or data-modifying consequences. In practice, this normalizes unsafe execution paths and makes it easier for an agent to perform unintended writes or destructive actions against live Stormboard data.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal