Intelligent search for agents. 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 is internally coherent: it needs one API key and makes network calls to the AIsa API, which is the expected behavior. Before installing, confirm you trust the AIsa service (api.aisa.one) and are comfortable sending queries/results to that provider. Use a scoped or limited API key if possible, avoid sending sensitive secrets or private data in queries, and monitor/rotate the key if you suspect misuse. Also verify the provider's privacy/retention policy and consider testing in a controlled environment first. If you need stronger assurance, ask the author for provenance (who maintains the skill and the service domains) and confirm the homepage/API domains are legitimate and expected.

Type: OpenClaw Skill Name: openclaw-aisa-search-web-academic-tavily Version: 1.0.0 The OpenClaw Search skill bundle is benign. All network communication from the `scripts/search_client.py` client is directed exclusively to `https://api.aisa.one`, which is the stated API endpoint for the service. There is no evidence of data exfiltration to unauthorized external endpoints, reading of sensitive local files (beyond environment variables), or execution of arbitrary commands. The `SKILL.md` file, treated as an attack surface, contains no prompt injection attempts or instructions that would cause an AI agent to deviate from its stated purpose of performing search queries and returning results.