browser-qa
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it navigates to external URLs and processes their content, including console errors and network logs.\n- Ingestion points: External target URLs and the resulting console/network data described in SKILL.md.\n- Boundary markers: The instructions lack markers or delimiters to separate untrusted website content from the agent's system instructions.\n- Capability inventory: The skill can navigate the browser, click links, submit forms, and perform login/logout sequences.\n- Sanitization: There is no mention of sanitizing or validating the data retrieved from external sites.
Audit Metadata