The Agent Skills Directory

[COMMAND_EXECUTION]: The skill operates by executing the gologin-local-agent-browser CLI for all profile and browser automation tasks. It also includes a local_browser_eval tool that allows the execution of arbitrary JavaScript within the active browser session for page inspection purposes.
[EXTERNAL_DOWNLOADS]: Documentation directs the user to install the gologin-local-agent-browser-cli package from NPM and provides links to the vendor's official GitHub repository (GologinLabs/gologin-local-agent-browser). These resources are provided by the skill's developer for its core functionality.
[DATA_EXFILTRATION]: The skill provides tools for exporting browser cookies (local_browser_cookies) and local/session storage (local_browser_storage). These features are intended to support persistence and profile handoffs in multi-account management workflows.
[PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted web content, creating a surface for indirect prompt injection.
Ingestion points: The local_browser_snapshot tool (referenced in SKILL.md and tools.md) captures the DOM of external web pages and provides it to the agent.
Boundary markers: The instructions do not specify the use of delimiters or specific markers to differentiate between user instructions and data retrieved from web pages.
Capability inventory: The skill enables powerful actions such as clicking, typing, and executing JavaScript (eval) based on the state of the ingested page content (tools.md).
Sanitization: There is no mention of sanitization or filtering applied to the web content before it is processed by the agent.

gologin-local-agent-browser-skill