Playwright PDF Export Automation
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Playwright library to launch and control a headless Chromium browser instance (
chromium.launch). - [EXTERNAL_DOWNLOADS]: The skill's installation instructions describe downloading the package from the
agentskillexchangerepository via thenpxcommand. - [DATA_EXFILTRATION]: The skill documentation describes capabilities for handling sensitive session cookies and authentication headers. It also includes functionality to upload generated PDF documents to external AWS S3 storage via the
putObjectAPI. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it retrieves and processes arbitrary external data from the web.
- Ingestion points: Target web content retrieved via the
page.goto()method (SKILL.md). - Boundary markers: There are no boundary markers or instructions to the agent to disregard commands embedded in the processed web content.
- Capability inventory: The skill possesses network access (S3 upload), browser manipulation (authentication injection), and local file system access.
- Sanitization: The documentation does not describe any sanitization or validation of the remote web content before it is rendered and processed.
Audit Metadata