playwright-scanner
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill suggests installing standard libraries such as
playwrightand@axe-core/playwrightfrom the NPM registry. These are industry-standard tools from well-known, trusted organizations. - [COMMAND_EXECUTION]: The skill executes internal browser-automation scripts to perform accessibility checks. These actions are appropriate for its stated purpose as a behavioral scanner and are executed in a restricted 'read-only' context.
- [INDIRECT_PROMPT_INJECTION]: Because the skill processes content from external URLs to perform its scans, it exposes a surface for indirect prompt injection.
- Ingestion points: External web content retrieved from user-provided URLs in
SKILL.md. - Boundary markers: No specific delimiters or safety instructions are defined to isolate untrusted web content.
- Capability inventory: The skill uses Playwright scripts to interact with and extract data from the browser DOM.
- Sanitization: There is no evidence of sanitization or filtering of the content retrieved from scanned web pages.
Audit Metadata