Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 8 major sources: Hacker News, GitHub Trending, Product Hunt, 36Kr, Tencent News, WallStreetCN, V2EX, and Weibo. Best for 'daily scans', 'tech news briefings', 'finance updates', and 'deep interpretations' of hot topics.
Security Analysis
medium confidenceThe skill's description matches an aggregator, but the runtime instructions expect local scripts and file reads that are not included (and give the agent broad discretion to fetch, extract, and store web content), which is internally inconsistent and potentially risky.
The declared purpose (aggregating and deeply analyzing multiple news sources) is plausible, but the SKILL.md expects a local script (scripts/fetch_news.py) and template files that are not present in the bundle. That mismatch means the skill as-published cannot operate without additional code or environment-provided tools.
Instructions direct the agent to run a local Python scraper, perform a broad 'deep' fetch that downloads and extracts article content, read templates.md from the skill directory, and write timestamped reports to reports/. Because no code or templates are included, the agent may attempt to locate or fetch missing files or run arbitrary local commands — giving it broad filesystem and network actions beyond the stated passive-aggregation description.
There is no install spec (instruction-only). That reduces installer risk because nothing is automatically downloaded or written by an installer. However, runtime commands still expect external scripts to exist.
The skill requests no environment variables, credentials, or config paths — which is proportionate for a read-only aggregator. Notably, it plans to fetch content from third-party sites without asking for credentials.
The skill does not request always:true and is user-invocable only. It does instruct saving reports to a reports/ directory (writing files), which is a modest persistence requirement but not an elevated platform privilege. Still, writing content fetched from arbitrary URLs can consume storage and persist potentially sensitive material.
Guidance
This skill's instructions assume there is a local script (scripts/fetch_news.py) and template files, but the package contains only SKILL.md — nothing to run. Before installing or invoking it, consider: 1) Ask the publisher for the missing scripts and templates or for a trusted source/repository URL so you can review the code. 2) If you must run it, run in a sandboxed environment (network- and filesystem-restricted) so the agent cannot fetch arbitrary code or read unrelated files. 3) Review any scripts (fetch_news.py, templates.md) yourself for scraping behavior, third-party libraries, and any places that might exfiltrate data. 4) Be aware it will download and extract article content (--deep) and save reports to disk; ensure you are comfortable with storing potentially copyrighted or sensitive content. 5) If you cannot obtain or inspect the missing files, do not enable the skill — the mismatch between description and required runtime files is a legitimate red flag.
Latest Release
v0.1.0
Initial release of News Aggregator Skill. - Fetches and deeply analyzes real-time news from 8 major sources (Hacker News, GitHub Trending, Product Hunt, 36Kr, Tencent News, WallStreetCN, V2EX, Weibo). - Supports both broad "Global Scan" and targeted keyword searches with automatic keyword expansion for domain coverage. - Adds deep fetching mode (`--deep`) to extract and include full article content. - Implements smart time filtering and annotated "smart fill" for sparse results, ensuring rich reports. - Provides interactive menu/help system triggered by specific user commands. - Generates concise, structured magazine-style reports in Chinese, saving each session's report to the `reports/` directory.
Popular Skills
Published by @tonyliu9189 on ClawHub
