playwright
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [External Package Download]: The skill uses
npxto download and install theplaywrightpackage and its Chromium browser binary from the official npm registry. This is a standard procedure for browser automation tasks. - [Command Execution]: The instructions involve executing terminal commands to manage directories, set environment variables, and run the Playwright CLI. This is necessary for the skill's intended functionality of capturing screenshots.
- [Indirect Prompt Injection Surface]: The skill processes a local file (
output/site/index.html) which may be populated with content from untrusted sources. - Ingestion points: The agent reads and processes
output/site/index.html(referenced inSKILL.md). - Boundary markers: No specific delimiters are present to separate untrusted content from the agent's instructions.
- Capability inventory: The skill uses
npxfor subprocess execution inSKILL.md. - Sanitization: No explicit sanitization or filtering is applied to the HTML content before processing.
Audit Metadata