testland/puppeteer-testing
Authors browser automation scripts using Puppeteer - Chrome / Chromium-only headless / headed automation, Page object via `page.*` API, network interception, PDF generation, screenshot capture, scraping. Distinct from Playwright (Puppeteer's older sibling, Chrome-only) - use Puppeteer for Chrome-only browser automation tasks (scraping, generating PDFs from HTML, screenshot pipelines) where Playwright's multi-browser support is unneeded overhead. Use when a project already depends on `puppeteer` / `puppeteer-core`, or when a Chrome-only script must emit PDFs, screenshots, or scraped data rather than assert on a page.
79
99%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill includes hardcoded plaintext credentials in the example test (email and password), which requires the LLM to emit those secret values verbatim in generated code/outputs.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The required runtime workflow shown in SKILL.md and references/use-cases.md uses Puppeteer to visit arbitrary web pages (e.g., `page.goto(...)`) and then reads/extracts page content via DOM evaluation (`page.$eval`, `page.$$eval`), meaning outsider-authored text from those visited sites can be ingested at runtime.
- Audited
- Security analysis