playwright

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (HIGH): The skill enables browser automation, presenting a high-severity attack surface for Indirect Prompt Injection. 1. Ingestion points: Untrusted external data enters the agent context through navigation (page.goto) and content selection (page.getByText, page.getByLabel) as seen in tests/login.spec.ts. 2. Boundary markers: The skill examples lack delimiters or instructions to ignore embedded commands within the ingested web content. 3. Capability inventory: The skill provides instructions for high-privilege actions including page.fill, page.click, and page.route in SKILL.md. 4. Sanitization: There is no evidence of sanitization, validation, or filtering of external content before it is processed by the agent.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 06:36 AM