Xpulse

Real-time X/Twitter social signal scanner for prediction market traders. Scans via DuckDuckGo (zero API cost) with two-stage local Qwen AI filtering: tradeab...

This skill appears to do what it says: it scrapes X via DuckDuckGo, analyzes posts with a local Qwen model (Ollama), and optionally gates alerts using your Kalshi positions. Before installing: 1) Review and confirm you trust the skill source (owner unknown) and inspect the included scripts (they are present and readable). 2) Place Kalshi credentials and private key in a secure config file (the skill reads ~/.openclaw/config.yaml or alternative paths); ensure file permissions restrict access. 3) Be aware the skill will create and store signal history and caches under ~/.openclaw/state (remove or encrypt if you don't want local persistence). 4) Ensure Ollama runs locally (localhost:11434) and that you are comfortable running a local LLM; the skill does not call any external LLM APIs. 5) Install Python dependencies from requirements.txt (ddgs, pyyaml, kalshi-python) in an isolated virtualenv. 6) If you want to be extra cautious, run the skill in an isolated environment or container to limit exposure of local state and keys. If you need the skill to avoid writing history, review/modify the code to change or disable state persistence before use.

Type: OpenClaw Skill Name: xpulse Version: 1.1.1 The Xpulse skill bundle is a legitimate tool designed for real-time social signal monitoring for prediction market traders. It implements a three-stage pipeline using DuckDuckGo for searching, a local Ollama (Qwen) instance for signal analysis, and the Kalshi API for position matching. The code follows security best practices, such as using a fail-closed design for its materiality gate, avoiding 'shell=True' in subprocess calls (scripts/xpulse.py), and directing sensitive API calls only to official endpoints (api.elections.kalshi.com). No evidence of data exfiltration, credential theft, or malicious prompt injection was found.