playwright_browser
Fail
Audited by Snyk on Feb 17, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.90). The prompt includes examples and usage patterns that embed plaintext passwords/credentials directly in actions JSON or inline CLI arguments (e.g., {"type":"fill","selector":"#password","value":"password"} or --actions '[...]'), which would require the agent to handle and output secret values verbatim and thus creates a high exfiltration risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). This skill directly visits and scrapes arbitrary public websites and search results (e.g., browser_tool.py, scraper.py, download_images.py, search.py, automator.py take user-provided URLs/queries and read page HTML, text, images, and search results), so it ingests untrusted third-party content that could contain indirect prompt injections.
Audit Metadata