playwright-patterns
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates web scraping, which creates a potential surface for indirect prompt injection.
- Ingestion points: The skill documents data extraction methods such as
textContent(),innerText(), andevaluate()inSKILL.md. - Boundary markers: No delimiters or instructions for isolating untrusted data are provided in the patterns.
- Capability inventory: The skill examples include powerful browser interaction capabilities such as
page.click()andpage.fill(). - Sanitization: No sanitization logic for extracted content is included in the provided snippets.
- [DYNAMIC_EXECUTION]: The skill documents the use of Playwright's methods for executing scripts in the browser.
- Evidence: Examples in
SKILL.mddemonstrate the use ofpage.evaluate()andpage.evaluateAll()to interact with the DOM and page-level JavaScript state.
Audit Metadata