ClawHub
Back to skill

Security audit

Book Braids

Security checks for vulnerabilities and agentic risk

Overview

This skill is for booking braid services, but it can create bookings and send contact details to an external service without clear consent or scoping instructions.

Review this skill before installing. It appears to do what it claims, but users should only invoke it when they intend to search or book through Lokuli, and the agent should ask for explicit confirmation before sharing contact details or creating an appointment.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill instructs use of an external MCP endpoint and includes a booking flow that transmits customer name, email, and phone number, but it does not warn the user that their personal data will be sent to a third-party service. In a booking context, this omission is especially risky because users may disclose sensitive contact information without informed consent, creating privacy, compliance, and trust issues.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger text is broad enough to activate on essentially any braids-related request, which can cause the agent to route users into an external booking flow even when they only want general information or recommendations. In this skill, that broad routing is more dangerous because the downstream tools can search providers and create bookings, increasing the chance of unintended third-party actions or premature sharing of user data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.