Omni Research

Multi-source deep research using your own browser. Queries Perplexity, Grok, and Gemini in parallel via CDP — zero API keys, uses your existing subscriptions.

Before installing or running this skill: 1) Review the code (research.py and browser.py) yourself — the scripts will control your browser via the Chrome DevTools Protocol and can read any page content. 2) Inspect ~/.config/omni-research/config.json after running setup; remove or set cliproxy_url only to a localhost service you control and replace any non-empty cliproxy_key with an empty string unless you intentionally run a local proxy. 3) Note the inconsistency: research.py sets a default cliproxy_key ('magi-proxy-key-2026') while setup.py uses an empty key — verify which value is in your config before use. 4) Run with a disposable browser profile or a browser instance started specifically for this tool (and ensure --remote-debugging-port is bound to localhost only); do NOT enable remote debugging on machines reachable by others. 5) If you do not want any external network calls, avoid using API-only mode (gemini-api) and ensure cliproxy_url is local. 6) If you are not comfortable granting full CDP control to third-party code, do not run it. If you decide to proceed, prefer running the code only after manual review and with conservative local configuration.

Type: OpenClaw Skill Name: omni-research Version: 1.0.0 The skill utilizes Chrome DevTools Protocol (CDP) to interact with the user's browser, which is a powerful capability that allows extensive control over browser tabs, including JavaScript execution (`eval_js` in `browser.py`). While the `eval_js` calls in this skill use hardcoded JavaScript and user queries are inserted via `Input.insertText` (safer), the inherent power of CDP and `eval_js` presents a significant vulnerability if not handled with extreme care or if the skill were to be modified. Additionally, the `research.py` script feeds extracted text from potentially untrusted websites into a synthesis LLM, creating a risk of indirect prompt injection or 'data poisoning' against the LLM, even though the synthesis prompt itself is designed for summarization. The `cliproxy_url` defaults to localhost, preventing direct external exfiltration by default, but the overall risk profile warrants a 'suspicious' classification due to these powerful and potentially exploitable capabilities.