browser-qa
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to visit, interact with, and process content from external URLs, which creates a potential surface for indirect prompt injection.
- Ingestion points: External websites, DOM content, console logs, and network request data (SKILL.md).
- Boundary markers: The instructions do not specify any delimiters or safety warnings to ensure the agent ignores instructions found within the external content it processes.
- Capability inventory: The skill leverages browser automation tools (Playwright, Puppeteer, Chrome) that allow the agent to navigate the web, submit forms, and interact with UI elements.
- Sanitization: There is no mention of filtering or sanitizing the content retrieved from the target websites before it is processed by the agent.
Audit Metadata