agent-browser
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
agent-browserpackage from the NPM registry, which is a well-known and standard service for Node.js dependencies. - [COMMAND_EXECUTION]: The skill operates by executing shell commands using the
agent-browserCLI to automate browser actions like clicking, typing, and capturing screenshots. This is the primary function of the skill. - [INDIRECT_PROMPT_INJECTION]: Because the skill is designed to navigate to external websites and retrieve their content (e.g., via
snapshotorget text), it creates an attack surface for indirect prompt injection. Content from external sites could be crafted to include instructions aimed at influencing the AI agent's logic during processing.
Audit Metadata