ClawHub
Back to skill

Security audit

InvoiceForge API

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward InvoiceForge API helper, but users should be aware it sends invoice and contact details to a third-party service.

Install this only if you intend to use InvoiceForge and are comfortable sending seller, buyer, invoice, email, and payment-status information to that service. Confirm account creation, invoice creation, status updates, and PDF recipients before allowing the agent to act, and store the API key only in an approved secret store.

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 (4)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The manifest description is extremely broad and claims applicability to essentially any invoicing or billing need. That can cause the skill to trigger in overly general business or financial contexts and solicit sensitive data when the user may not have intended to use this third-party service. In a billing workflow, overbroad activation increases the chance of unnecessary disclosure of business and client information.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
This section instructs the agent to collect an email address and transmit it to a third-party API to create an account, but it provides no explicit consent, privacy, or data-handling warning. Because invoice workflows involve personal and business contact data, silent collection and transmission can expose users to unwanted account creation, privacy violations, or compliance issues.

External Transmission

Medium
Category
Data Exfiltration
Content
### Step 2: Sign Up via API
```bash
curl -X POST https://invoiceforge.vosscg.com/v1/keys \
  -H "Content-Type: application/json" \
  -d '{"email":"user@example.com"}'
```
Confidence
93% confidence
Finding
The skill includes an external POST request that transmits the user's email address to a remote service for account creation. External transmission is expected for this kind of integration, but it is still security-relevant because it sends user data off-platform and could create an account without adequately informed consent.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The workflow tells the agent to download and share invoice PDFs containing billing records, names, emails, addresses, and financial details without any warning about secure storage, retention, or recipient verification. Invoices are sensitive financial documents, so mishandling them can lead to data leakage or accidental disclosure to unauthorized parties.

Static analysis

No suspicious patterns detected.