KDP Publisher

• Analyzed: May 12, 2026, 4:14 AM
• Findings: 1
• Version: 1.0.0
• Hash: 61d260db0e8093c5fb7ff78297a631b9dd362426b591d1e36a7b51d599bd7f30
• Source: palm
• External report: View on VirusTotal

Findings (1)

The skill bundle is designed for legitimate KDP book publishing, leveraging AI for content generation and browser automation for KDP uploads. It is classified as 'suspicious' due to the inclusion of high-risk capabilities, particularly the explicit instructions in `SKILL.md` for the AI agent to perform direct browser DOM manipulation via JavaScript `evaluate` and file uploads using CDP `DOM.setFileInputFiles`. While these actions are presented within the legitimate context of KDP interaction, they represent powerful primitives that, if combined with a prompt injection vulnerability in the OpenClaw agent's execution model, could be exploited to perform unauthorized actions, data exfiltration, or arbitrary code execution within the browser context. The Python scripts themselves (`scripts/*.py`) are well-aligned with the stated purpose and do not exhibit malicious intent, but their execution via the agent also presents a potential shell injection vulnerability if user inputs are not properly sanitized.