gemini-computer-use

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass, no license.

Audit 0.4.1 · source sha 31eb89d791f0 · 26 Oct 2026Report an issue or request a re-scan

• Publisheram-will GitHub userOwner of the repository this skill is read from
• Source folderam-will/codex-skills/skills/gemini-computer-useThe exact folder we audited
• LicenceNot declaredAs the repository states it
• Commit pinned for this verdict31eb89d791f0A new audit runs when the source changes
• Repository statusNot archivedLast push 103 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Build and run Gemini 2.5 Computer Use browser-control agents with Playwright. Use when a user wants to automate web browser tasks via the Gemini Computer Use model, needs an agent loop (screenshot → function_call →…

---
name: gemini-computer-use
description: Build and run Gemini 2.5 Computer Use browser-control agents with Playwright. Use when a user wants to automate web browser tasks via the Gemini Computer Use model, needs an agent loop (screenshot → function_call → action → function_response), or asks to integrate safety confirmation for risky UI actions.
---

# Gemini Computer Use

## Quick start

1. Source the env file and set your API key:

   ```bash
   cp env.example env.sh
   $EDITOR env.sh
   source env.sh
   ```

2. Create a virtual environment and install dependencies:

   ```bash
   python -m venv .venv
   source .venv/bin/activate
   pip install google-genai playwright
   playwright install chromium
   ```

3. Run the agent script with a prompt:

   ```bash
   python scripts/computer_use_agent.py \
     --prompt "Find the latest blog post title on example.com" \
     --start-url "https://example.com" \
     --turn-limit 6
   ```

## Browser selection

- Default: Playwright's bundled Chromium (no env vars required).
- Choose a channel (Chrome/Edge) with `COMPUTER_USE_BROWSER_CHANNEL`.
- Use a custom Chromium-based executable (e.g., Brave) with `COMPUTER_USE_BROWSER_EXECUTABLE`.

If both are set, `COMPUTER_USE_BROWSER_EXECUTABLE` takes precedence.

## Core workflow (agent loop)

1. Capture a screenshot and send the user goal + screenshot to the model.
2. Parse `function_call` actions in the response.
3. Execute each action in Playwright.
4. If a `safety_decision` is `require_confirmation`, prompt the user before executing.
5. Send `function_response` objects containing the latest URL + screenshot.
6. Repeat until the model returns only text (no actions) or you hit the turn limit.

## Operational guidance

- Run in a sandboxed browser profile or container.
- Use `--exclude` to block risky actions you do not want the model to take.
- Keep the viewport at 1440x900 unless you have a reason to change it.

## Resources

- Script: `scripts/computer_use_agent.py`
- Reference notes: `references/google-computer-use.md`
- Env template: `env.example`

Excerpt, first 2,075 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

pip install google-genai playwright

git clone https://github.com/am-will/codex-skills
git -C codex-skills checkout 31eb89d791f0

Works in

1. 2026-10-26
   ✓SAFE B 89 / 100

   first audit · source 31eb89d791f0

Questions about gemini-computer-use

• github.com/am-will/codex-skills/tree/main/skills/gemini-computer — the audited source at commit 31eb89d791f0 and every finding aboveObserved · 26 Oct 2026

Spotted something wrong? Report a correction · Methodology