News Aggregator Skill

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.

This package is missing the scripts and templates it instructs the agent to run and read. Before installing or enabling: (1) Ask the publisher for the missing files (scripts/fetch_news.py, templates.md, any scripts referenced) so you can review them — especially the 'deep' fetching logic that downloads and extracts article content. (2) Confirm whether any credentials/cookies are needed for sources like Weibo/Tencent and why those are not declared. (3) If you plan to run it, run the code in a sandbox and inspect network behavior (which domains are contacted, whether it follows arbitrary links, and whether it uploads data elsewhere). (4) Consider requiring the skill be user-invocable only or disabling autonomous invocation until you vet the implementation. Given the current mismatch between claims and provided files, do not grant broad runtime trust yet.

Type: OpenClaw Skill Name: news-aggregator-skill-4 Version: 0.1.0 The `SKILL.md` file instructs the AI agent to automatically expand user-provided keywords (e.g., 'AI' to 'AI,LLM,GPT,...') before passing them to the `fetch_news.py` script. This is a form of prompt injection where the agent modifies user input based on internal instructions. While the immediate objective of this keyword expansion is benign (improving search results), it demonstrates a risky capability for the agent to alter user input, which could be a vector for injecting unintended arguments or commands under different instructions. Additionally, the skill involves downloading and parsing content from external websites via the `--deep` flag, which is a high-risk operation, though necessary for its stated purpose.