ClawHub
Back to skill

Security audit

Molthouse Casino

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed casino integration, but it enables real-value deposits, withdrawals, and betting without clear user-confirmation safeguards.

Review this carefully before installing. Only use it when you intentionally want an agent to interact with Molthouse, and require explicit approval for every deposit, withdrawal, and bet. Treat API keys and deposit addresses as sensitive, and assume USDC transfers and gambling losses may not be reversible.

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 (3)

Missing User Warnings

High
Confidence
97% confidence
Finding
The documentation enables deposits, withdrawals, and gambling with USDC-backed credits but does not prominently warn about irreversible blockchain transfers, potential loss of funds, withdrawal fees, or gambling risk. In this context, omission of these warnings is dangerous because an agent could encourage or automate financially risky actions without informed user consent.

Vague Triggers

Medium
Confidence
97% confidence
Finding
The skill description is broadly scoped to trigger on generic requests like wanting to "gamble" or "interact with the platform," which increases the chance an agent invokes a high-risk financial skill in situations where the user did not explicitly consent to wagering or fund transfers. In a skill that can register accounts, move USDC, and place bets, overbroad activation materially raises the risk of unintended financial actions.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
# 1. Register
curl -X POST $BASE/v1/auth/register -H 'Content-Type: application/json' \
  -d '{"agent_name":"my_agent"}'
# → { api_key: "mh_sk_...", agent_id: "..." }
Confidence
82% confidence
Finding
The skill instructs the agent to transmit data to an external service, including registration details and authenticated account actions, which creates privacy, credential-handling, and financial-risk exposure. While external API use is expected for this skill, it becomes security-relevant because the same workflow issues API keys and supports deposits, withdrawals, and gambling actions against a third-party service.

Static analysis

No suspicious patterns detected.