ClawHub
Back to skill

Security audit

Skill

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed banking integration, but it auto-runs mutable GitHub code with a sensitive banking API key.

Install only if you are comfortable giving this MCP server access to your Brighty owner API token. Prefer a pinned, reviewed commit or vetted package release, use the least-privileged revocable token available, keep payout confirmations outside the MCP server, and monitor or rotate the token if the dependency changes.

A.I.G

Vulnerability Patterns
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Findings (1)

T03 · Remote Payload Retrieval and Execution

Error
Location
config/mcporter.json:4
Finding

Unpinned Remote GitHub Package Is Automatically Downloaded and Executed with Banking Credentials

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • 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)

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 31)May include surrounding context.

md
### 2. Get API key

Go to [Account > Business](https://business.brighty.app/account/business) and click **Create API Token**. Only the business **owner** can do this.

### 3. Configure

Rp1

Medium
Category
MCP Rug Pull
Confidence
97% confidence
Finding

The skill instructs users to launch an MCP server directly from a GitHub source via npx -y github:Maay/brighty_mcp without pinning a specific commit or immutable version. This creates a supply-chain risk: the referenced code can change over time or be compromised, and because the skill handles banking actions and an API key, a malicious update could exfiltrate credentials or execute unauthorized financial operations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.