The Agent Skills Directory

[COMMAND_EXECUTION]: Employs the official browse CLI for core development tasks including project initialization, local testing, and cloud publishing. These operations are consistent with the platform's documented usage.
[EXTERNAL_DOWNLOADS]: Dependencies are managed through standard package managers, pulling official SDKs such as @browserbasehq/sdk-functions and playwright-core from established registries.
[PROMPT_INJECTION]: As the skill involves automated browser interactions with external websites, it possesses an attack surface for indirect prompt injection.
Ingestion points: External data enters the agent context via browser navigation and content extraction commands in SKILL.md and REFERENCE.md.
Boundary markers: Code examples do not demonstrate the use of delimiters to isolate untrusted web content from the agent's instructions.
Capability inventory: The skill provides tools for browser control and cloud deployment, which includes network access.
Sanitization: Standard browser automation workflows are described without explicit prompt-level sanitization for ingested content.

functions