ClawHub

AI News Collector

v1.0.0

AI 新闻聚合与热度排序工具。当用户询问 AI 领域最新动态时触发，如："今天有什么 AI 新闻？""总结一下这周的 AI 动态""最近有什么火的 AI 产品？""AI 圈最近在讨论什么？"。覆盖：新产品发布、研究论文、行业动态、融资新闻、开源项目更新、社区病毒传播现象、AI 工具/Agent 热门项目。输出中文...

⭐ 0· 51·0 current·0 all-time
by@modestyrichards
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description match the actual instructions: the SKILL.md describes multi-dimensional web searches, source lists, deduplication and ranking — all appropriate for a news-collection skill. No unrelated credentials, binaries, or system paths are requested.
✓
Instruction Scope
Runtime instructions restrict actions to web searches, fetching articles, cross-checking sources, deduplication and ranking. They do not instruct reading local files, requesting unrelated environment variables, or exfiltrating agent secrets. The only operational note is use of web_fetch/search-style operations, which is expected for a web-aggregation skill.
✓
Install Mechanism
No install spec and no code files — instruction-only. README includes optional manual install/clone instructions pointing to a GitHub repo, but the skill itself does not require installation or run any downloaded code. No archive downloads or third-party install hosts are used by the skill at runtime.
✓
Credentials
The skill requests no environment variables, credentials, or config paths. Suggested data sources are public news, newsletters, social platforms and GitHub — appropriate for the stated purpose.
✓
Persistence & Privilege
always is false and model invocation is allowed (the platform default). The skill does not request persistent system-wide presence or attempt to modify other skills or system configuration.
Assessment
This skill is internally coherent, but review a few practical safety points before enabling: (1) The SKILL.md expects the agent to perform many web fetches — confirm your agent is allowed to access the web and that you’re comfortable with it making multiple outbound requests. (2) The README suggests cloning a GitHub repo for manual install; avoid running arbitrary install scripts from unknown repos unless you inspect them. (3) The skill links to an external "Complete setup guide" (skillboss.co) — verify that link before following setup steps. (4) Expect it to surface paywalled content and public social posts; be mindful of copyright and scraping policies of target sites. (5) If you have strict data-exfiltration or privacy constraints, ensure the agent’s web access is sandboxed or disable the skill. Otherwise the skill appears proportionate for a news-aggregation purpose.

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

aivk97bx3bhy0prh04d00s4prrka184pd52collectorvk97bx3bhy0prh04d00s4prrka184pd52curationvk97bx3bhy0prh04d00s4prrka184pd52latestvk97bx3bhy0prh04d00s4prrka184pd52newsvk97bx3bhy0prh04d00s4prrka184pd52

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments