The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute the browse CLI and its associated subcommands for web automation.
[EXTERNAL_DOWNLOADS]: The skill documentation provides instructions for the user to manually install necessary dependencies, including the @ulpi/browse CLI (a vendor resource) and the camoufox-js library. It explicitly advises against automatic installation by the agent.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it retrieves and processes content from external websites.
Ingestion points: Untrusted data enters the agent's context through the browse ... goto <url> command and subsequent content extraction (e.g., text, snapshot).
Boundary markers: The instructions do not mandate the use of delimiters or specific instructions to the agent to ignore embedded commands in the fetched content.
Capability inventory: The agent possesses the Bash tool, which could be exploited if the agent obeys instructions found on a malicious website.
Sanitization: The skill does not describe any sanitization or validation mechanisms for the data retrieved from external sources.

browse-stealth