ClawHub
Back to skill

Security audit

OpenTable

Security checks across malware telemetry and agentic risk

Overview

The supplied evidence describes a hospitality operations guidance skill and does not show hidden automation, credential capture, persistence, or destructive behavior.

Review the skill as operational guidance for hospitality incidents. It appears safe to install based on the supplied evidence, but users should still avoid entering credentials or unnecessary sensitive guest details and should keep any real reservation changes under normal business approval controls.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
- avoid storing sensitive guest details in long-lived notes
- document only what is required for operational decisions

Never ask users to paste credentials or private account tokens into chat.

## Common Traps
Confidence
80% 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.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
| Class | Typical Symptom | Immediate Priority |
|------|------------------|--------------------|
| Overbooking | More covers than seatable capacity | Protect in-house service and communicate options |
| Confirmation failure | Guests claim no confirmation or wrong time | Reconcile reservation state and reduce arrival friction |
| Availability mismatch | Slots shown despite operational block | Stop new exposure and correct inventory quickly |
| Outage or degraded platform | Booking flow unavailable or unstable | Activate fallback intake and preserve guest trust |
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.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.