Model Council Pro

Multi-model consensus system — send a query to 3+ different LLMs via OpenRouter simultaneously, then a judge model evaluates all responses and produces a win...

This skill appears to do what it says: it uses your OPENROUTER_API_KEY to call OpenRouter and aggregate multiple model outputs. Before installing, consider: (1) Cost and billing — calls to multiple models (and a judge model) can incur non-trivial charges; monitor usage and set quotas. (2) Data exposure — prompts and model outputs are sent to OpenRouter and the upstream model providers and may be logged; avoid sending secrets or sensitive data. (3) Verify the OPENROUTER_API_KEY you provide has appropriate scope/limits and rotate keys if you later remove the skill. (4) If you need stricter privacy, confirm OpenRouter's logging/retention policy or run a trusted in-house routing endpoint. Overall the skill is coherent and consistent with its purpose; proceed if you accept the cost and data-exposure tradeoffs.

Type: OpenClaw Skill Name: model-council-pro Version: 1.0.0 The OpenClaw AgentSkills bundle for 'model-council-pro' is benign. The `SKILL.md` file clearly describes the skill's purpose and usage, providing standard command examples without any prompt injection attempts against the OpenClaw agent. The `scripts/model_council.py` script correctly retrieves the `OPENROUTER_API_KEY` from environment variables and uses `urllib.request` to interact with the OpenRouter API. It processes user input via `argparse` and constructs JSON payloads for LLM interactions, avoiding common shell or command injection vulnerabilities. There is no evidence of data exfiltration, persistence mechanisms, or other malicious activities.