ClawHub

Beamer

Security checks across malware telemetry and agentic risk

Overview

This is a real Beamer integration, but it gives agents broad ability to create, update, delete, and proxy Beamer API requests without enough guardrails.

Review before installing. Use this only with a Beamer account whose permissions you are comfortable delegating through Membrane, and require the agent to show the exact target and obtain explicit approval before any create, update, delete, publishing, or raw proxy request.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

Medium
Confidence
93% confidence
Finding
The manifest description materially understates the skill's capabilities. The body documents not only user/filter management but also posts, comments, feature requests, deletions, and even proxy access to arbitrary Beamer API endpoints, which can cause the orchestrator or user to invoke the skill without understanding its true authority and risk surface.

Vague Triggers

Medium
Confidence
85% confidence
Finding
The invocation text is broad enough to match many generic Beamer-related requests, increasing the chance the skill is selected in situations where its destructive or high-privilege features are not expected. Overbroad routing can lead to unintended execution of sensitive actions through a skill that also supports deletion and arbitrary API proxying.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The documentation advertises destructive actions such as deleting users, comments, and posts without any caution, confirmation requirement, or mention of irreversible consequences. In an agent context, that omission increases the risk of accidental or overly eager destructive execution against production Beamer data.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal