Multi-source retrieval with confidence scoring - web, academic, and Tavily in one unified API

Intelligent search for agents. Multi-source retrieval with confidence scoring - web, academic, and Tavily in one unified API.

This skill appears to do what it claims: it sends your queries and any URLs you supply to the AIsa service (api.aisa.one) and returns aggregated, confidence-scored results. Before installing, consider: (1) AISA_API_KEY will grant the skill access to that third‑party API—restrict the key's scope if possible and monitor its usage/quotas; (2) any URLs or query text you pass (including internal or private URLs) will be transmitted to the external service—avoid sending sensitive internal endpoints or secrets; (3) verify the legitimacy of the api.aisa.one provider and the publisher (skill source is unknown) if you need stronger provenance guarantees; (4) curl is only used in examples — the Python client performs network calls itself; ensure python3 will run in your environment. If you need higher assurance, request the maintainer's provenance, an official homepage for the API, or run the included script in a restricted environment with a least-privilege API key.

Type: OpenClaw Skill Name: openclaw-aisa-search-website-academic-tavily-serp-exa Version: 1.0.0 The skill bundle provides a client for the AIsa search API, enabling multi-source web and academic searches. The `scripts/search_client.py` uses standard Python libraries (`urllib.request`, `os.environ.get`) to make authenticated HTTP POST requests to `https://api.aisa.one` using the `AISA_API_KEY`. User input for search queries is safely passed as URL parameters or JSON data, without any evidence of command injection or arbitrary code execution. The `SKILL.md` documentation clearly outlines the skill's purpose and usage, and does not contain any prompt injection attempts or instructions for the agent to perform unauthorized actions. All observed behaviors are directly aligned with the stated purpose of providing an intelligent search capability.