playwright_browser
Fail
Audited by Snyk on Feb 16, 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: 0.90). This skill fetches and processes arbitrary public web content (e.g., browser_tool.py reads page HTML, scraper.py extracts text/attributes from arbitrary URLs, download_images.py downloads images from sites, search.py scrapes Baidu results, and automator.py executes/evaluates page JS), so it clearly ingests untrusted third‑party/user‑generated content that the agent reads and interprets.
Audit Metadata