ClawHub

Multi Source Search

v1.0.0

Run confidence-scored multi-source retrieval through AIsa. Use when: the user needs cross-source verification, consensus checks, or one report that compares...

⭐ 0· 62·0 current·0 all-time
by@baofeng-tech

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for baofeng-tech/multi-source-search.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Multi Source Search" (baofeng-tech/multi-source-search) from ClawHub.
Skill page: https://clawhub.ai/baofeng-tech/multi-source-search
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Required env vars: AISA_API_KEY
Required binaries: python3
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install multi-source-search

ClawHub CLI

Package manager switcher

npx clawhub@latest install multi-source-search
Security Scan
Capability signals
Requires sensitive credentials
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (multi-source retrieval, confidence scoring) align with the requested binary (python3), the single required env var (AISA_API_KEY), and the included Python client which calls AIsa endpoints. There are no unrelated credentials or binaries requested.
✓
Instruction Scope
SKILL.md instructs running the bundled scripts (scripts/search_client.py) and to provide AISA_API_KEY; the script sends queries/URLs to AIsa endpoints. The instructions do not ask the agent to read arbitrary local files, other environment variables, or to exfiltrate data to unexpected endpoints beyond the declared AIsa API.
✓
Install Mechanism
No install spec is provided (instruction-only runtime plus shipped script). No downloads from arbitrary URLs or archive extraction. Risk from installation is low because nothing is automatically fetched during install.
✓
Credentials
Only one credential (AISA_API_KEY) is required and used directly as a Bearer auth token in requests to the AIsa API. The requested env var is appropriate and proportional to the skill's functionality. The code checks for the key and will error if absent.
✓
Persistence & Privilege
The skill is not forced-always (always: false) and does not request elevated or cross-skill config changes. It can be invoked by the agent (normal behavior) but has no persistent installation actions defined.
Assessment
This skill appears to be what it says: a Python client that sends queries/URLs to the AIsa API. Before installing, consider: (1) AISA_API_KEY will be sent as a Bearer token to https://api.aisa.one — do not use a shared or highly-privileged key if you have sensitive data or limited-trust keys; create a dedicated, limited-scope key if possible. (2) Any queries or URLs you submit will be transmitted to AIsa's servers—avoid sending secrets or private documents unless you trust the provider and understand their data retention/privacy policies. (3) Review the included scripts/search_client.py (already present) to confirm there are no additional endpoints you don't expect and to verify behavior for error handling and retries. (4) If you require stricter control, run the script locally with a sandboxed/limited API key or inspect network traffic during a test run. Overall, the package is internally consistent but relies on an external service — treat the AISA_API_KEY like any other sensitive credential.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

🔎 Clawdis
Binspython3
EnvAISA_API_KEY
Primary envAISA_API_KEY
latestvk973khdnggadv74jegynhnn0t985edpp
62downloads
0stars
1versions
Updated 3d ago
v1.0.0
MIT-0
@baofeng-tech
latest
Download

Multi-Source Search Verification Engine

Run confidence-scored multi-source retrieval through AIsa. Use when: the user needs cross-source verification, consensus checks, or one report that compares multiple search surfaces. Supports parallel retrieval, confidence scoring, and synthesis-ready outputs.

When to use

  • The user wants the same topic checked across multiple search surfaces instead of trusting one provider.
  • The user needs confidence scoring, consensus checks, or a comparison across multiple search lanes.
  • The user wants synthesis-ready validation before making a recommendation.

High-Intent Workflows

  • Run parallel retrieval and compare the returned signals.
  • Check whether a claim appears across multiple search surfaces.
  • Turn multi-source retrieval into a confidence-scored research brief.

Quick Reference

  • python3 scripts/search_client.py --help

Setup

  • AISA_API_KEY is required for AIsa-backed API access.
  • Use repo-relative scripts/ paths from the shipped package.
  • Prefer explicit CLI auth flags when a script exposes them.

Example Requests

  • Compare how three search surfaces describe the latest browser-use agent products
  • Verify whether a market claim appears in web, scholar, and cited answer results
  • Run a confidence-scored research pass on multi-agent IDEs before writing a recommendation

Guardrails

  • Do not market this package as the generic one-search entry point.
  • Do not claim consensus that the returned results do not support.
  • If some providers time out, explain how that affects the score.

Comments

Loading comments...