The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute various commands for the Browserbase CLI (browse), covering platform operations and local browser driving.\n- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the browse CLI from the npm registry and clones starter templates from official Browserbase repositories.\n- [REMOTE_CODE_EXECUTION]: The skill employs npm for global package installation and npx (via browse skills install) to execute a remote installation script for agent skills.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection when retrieval tools (fetch, search) ingest untrusted content from the web.\n
Ingestion points: Data is retrieved from external websites via browse cloud fetch and browse cloud search as described in SKILL.md and REFERENCE.md.\n
Boundary markers: Absent; there are no instructions to delineate or ignore potential commands within fetched content.\n
Capability inventory: The skill has full Bash access and the ability to upload files and perform network operations via the CLI.\n
Sanitization: No sanitization or filtering is applied to web content before it enters the agent's context.

browserbase-cli