ClawHub
Back to skill

Security audit

Pressmark Document Lifecycle & Billing

Security checks for vulnerabilities and agentic risk

Overview

This skill uses a clearly identified billing service to make the invoice and payment-record changes you request.

Use Pressmark only if it is suitable for your billing data, and check its privacy and retention terms before submitting confidential information. Verify the selected document, payment amount, and resulting status when requesting changes.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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 (1)

The workflow sends billing and payment information to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The workflow directs the agent to process invoices and payment details through a third-party MCP service without requiring disclosure of the data transfer or checking whether that service is approved for sensitive billing information. Naming Pressmark and requiring users to connect it makes the integration transparent and reduces suspicion, but does not establish informed authorization to transmit customer or financial data. This is a potential privacy and compliance exposure, not evidence of malicious exfiltration or publicly accessible records.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.