agent-browser
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation includes instructions to install the 'agent-browser' CLI globally and download Chromium binaries via 'agent-browser install'. These dependencies are fetched from external sources at runtime.
- [INDIRECT_PROMPT_INJECTION]: The tool is designed to read and interact with external web pages, which poses a risk of indirect prompt injection.
- Ingestion points: Untrusted data is ingested into the agent context through commands such as 'snapshot', 'get text', and 'get html' as described in SKILL.md.
- Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from following directions embedded in web content.
- Capability inventory: The agent possesses interaction capabilities like 'click', 'fill', and 'type' that can be manipulated by malicious web content (SKILL.md).
- Sanitization: There is no description of sanitization or validation for the content retrieved from web pages before it is processed by the agent.
Audit Metadata