LLM-as-a-Judge evaluator via Langfuse. Scores traces on relevance, accuracy, hallucination, and helpfulness using GPT-5-nano as judge. Supports single trace...

This skill largely does what its README says, but there are several red flags you should resolve before running it in a production environment: 1) The script contains hardcoded Langfuse API keys and a hardcoded Langfuse host and uses those values directly — that could send your trace data (or allow the script to act using somebody else's account). Treat those embedded keys as suspicious and do not rely on them. 2) The script will attempt to read ~/.openclaw/workspace/.env for an OPENROUTER_API_KEY if you don't set one in the environment; that file may contain unrelated secrets. The skill metadata did not declare that config path. 3) Dependencies (requests, openai, langfuse) are not declared; running without knowing what will be installed is fragile. Recommended actions before installing/using: - Inspect the evaluator.py file fully (remove or rotate any embedded keys). - Replace hardcoded LF_AUTH/LF_API with explicit env-based configuration and ensure the host points to a Langfuse instance you control. - Avoid running the script as-is on systems with sensitive ~/.openclaw/workspace/.env files; run it in an isolated test environment or container first. - If you need to trust this skill, ask the publisher to provide a version that reads credentials only from declared env vars (no defaults), documents required Python packages, and documents exactly which endpoints will receive data. If the publisher confirms the embedded keys are inert placeholders and the code is changed to respect environment values only, the concerns would be reduced.

Type: OpenClaw Skill Name: llm-evaluator-pro Version: 1.0.0 The skill is classified as suspicious due to two key vulnerabilities found in `scripts/evaluator.py`. Firstly, it attempts to read the `OPENROUTER_API_KEY` from `~/.openclaw/workspace/.env` if not found in environment variables, which is a local file inclusion/information disclosure risk, granting the skill access to a potentially sensitive file within the OpenClaw workspace. Secondly, it contains hardcoded Langfuse API keys (`sk-lf-115cb6b4-7153-4fe6-9255-bf28f8b115de`, `pk-lf-8a9322b9-5eb1-4e8b-815e-b3428dc69bc4`) and an internal host (`http://langfuse-web:3000`), which, while potentially overridden by environment variables, represents poor security practice and a potential credential leak if these keys were sensitive and used in an unintended context.