ClawHub
Back to skill

Security audit

Beszel

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Beszel monitoring helper that stores optional local notes only after user confirmation.

Before installing, expect the skill to help with Beszel monitoring operations and optionally keep local operational notes in ~/beszel/. Review what it proposes to save, avoid storing credentials in those notes, and only approve proactive activation for the monitoring contexts you actually want.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
- Use concise natural-language notes, not exposed config keys.
- Update `last` whenever monitoring context changes.
- Promote repeated incidents into prevention rules.
- Never delete prior context without confirmation.
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The activation guidance uses broad trigger topics such as 'monitoring alerts,' 'node health,' and 'agent failures,' which are common phrases that can appear in many adjacent support contexts. This can cause the skill to activate outside the user's intended scope, leading to unsolicited behavior, over-collection of operational context, or inappropriate persistence of monitoring-related preferences across conversations.

Missing User Warnings

Low
Confidence
94% confidence
Finding
The skill explicitly instructs creation of `~/beszel/memory.md`, which is a local filesystem write in the user's home directory, but it provides no user-facing consent step, warning, or boundary on when that write should occur. Even though the content is a benign memory template, silent persistence to local files can surprise users, overwrite prior notes, or normalize unauthorized state changes by the agent.

Static analysis

No suspicious patterns detected.