ClawHub
Back to skill

Security audit

Buildium

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Buildium helper for reading connected account data, with broad routing language but no artifact-backed hidden writes or destructive behavior.

Install this only if you want an agent to read data from your connected Buildium account through OOMOL. Keep the connected Buildium/OOMOL permissions limited to data you are comfortable exposing, and review future versions carefully if they add tagged write or destructive actions.

SkillSpector

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

High
Confidence
97% confidence
Finding
The manifest and description claim the skill is only for 'searching and reading data,' but the body explicitly contemplates write and destructive actions. This mismatch can cause an agent or reviewer to grant the skill broader trust than intended, increasing the chance of unauthorized state-changing operations in Buildium.

Intent-Code Divergence

Medium
Confidence
94% confidence
Finding
The safety section states that untagged actions are reads, while also documenting possible write and destructive actions, contradicting the earlier representation that the skill is only for reading/searching. In skill-driven automation, this kind of ambiguous safety contract can mislead orchestration logic or human operators into treating the skill as low risk when it may perform state changes.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The instruction to use this skill for 'ANY Buildium request' is overly broad and can cause unintended invocation across all Buildium-related tasks. In context, that becomes more dangerous because the same file suggests the skill may encompass state-changing actions, so broad routing could steer sensitive operations into a tool users or agents assume is only for safe reads.

Static analysis

No suspicious patterns detected.