qianfan-deepresearch

SuspiciousCK: Medium

by ide-rea

7.0K downloads2 starsv1.1.411 versions

Description

调用百度千帆 DeepResearch Agent API 自动生成深度研究报告（输出 Markdown 与 HTML 两种格式），一键完成「创建会话 → 发起研究 → 自动跳过澄清 → 自动确认大纲 → 获取报告下载链接」完整流程。支持三种深度模式：lite（轻量版，速度快，默认）/ standard（标准...

Changelog

Version 1.1.4 of deepresearch-conversation — major update and rebranding. - Renamed skill to "qianfan-deepresearch" and updated the description for greater clarity and coverage. - Streamlined the workflow: switched to a single-step, fully automated bash script execution that outputs report download links in Markdown and HTML. - Introduced deep research versions: lite (default), standard, pro; includes explicit mapping rules triggered by specific user keywords. - Set strict guidelines for query generation, with clear rules for use, required clarifications, and which user inputs map to which research depth. - Standardized user-facing output with a fixed template; all responses now strictly follow the mandated format, forbidding extra commentary or formatting. - Deprecated manual SSE/HTTP workflow in favor of a robust wrapper script; users/agents must now always call scripts/deepresearch.py with proper long timeouts and parse only its stdout JSON. - Enhanced resource section and practical examples to illustrate real-world usage and correct input/output patterns.

Published Feb 7, 2026Updated May 7, 2026

Security Analysis

ClawHub:

Suspicious

Clawkeeper:

CK: Medium

Risk Score5.0 / 10

Multiple risk signals — review findings before installing. Score is the sum of weighted findings below.

Findings

4 files analyzed

medium|+2.0 pts

Contains executable handler files (js/ts/sh/py)

critical|+3.0 pts

Flagged as suspicious by ClawHub

ClawHub scanned: May 7, 2026

Rescanned every 6 hours by Clawkeeper

Deploy Securely

Free to scan. Pro to deploy.