The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the official @browserbasehq/cli and @browserbasehq/browse-cli packages from the npm registry, as well as running a skill installer via npx.
[COMMAND_EXECUTION]: The skill uses the Bash tool to run bb CLI commands for automation, session management, and platform interactions.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it retrieves and processes content from arbitrary external URLs, which could contain instructions intended to manipulate the agent's behavior.
Ingestion points: Data enters the agent context through the bb fetch <url> and bb search "<query>" commands described in SKILL.md and REFERENCE.md.
Boundary markers: The skill lacks explicit delimiters or system instructions to ignore potential commands embedded within the retrieved web content.
Capability inventory: The skill is granted access to the Bash tool, which allows for shell command execution that could be targeted by injected instructions.
Sanitization: There is no evidence of content sanitization or validation before the agent processes the retrieved data.

browserbase-cli