playwright-browser-type

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted data and uses it to perform browser-based actions.
  • Ingestion points: The text and ref properties in the arguments schema in SKILL.md accept external input.
  • Boundary markers: No delimiters or instructions are present to prevent the agent from obeying instructions embedded in the processed data.
  • Capability inventory: The skill can type text and submit forms in a browser session via the Playwright browser_type tool.
  • Sanitization: No sanitization, escaping, or validation of the input text is performed before it is interacted with in the browser context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 08:28 PM