ClawHub

Morning Briefing AI News

v0.1.0

AI industry news aggregation from curated RSS feeds. Catches model releases from major labs.

⭐ 0· 77·0 current·0 all-time
by@justintieu
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Pending
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The skill is an RSS-based news aggregator and only requires access to a curated list of feed URLs (feeds.json). It declares no binaries, credentials, or unrelated resources, which is appropriate for the stated purpose.
✓
Instruction Scope
Runtime instructions are limited to reading feeds.json, fetching RSS/Atom feeds via web_fetch, parsing and filtering items, optional deduplication/categorization, and optionally writing briefing files when the user explicitly requests --save. There are no instructions to read unrelated system files, access credentials, or post data to unexpected endpoints. It will contact external feed URLs (including raw.githubusercontent.com for some feeds) — expected for an RSS aggregator.
✓
Install Mechanism
There is no install spec and no code files to write or execute. Being instruction-only minimizes install-time risk.
✓
Credentials
The skill declares no environment variables, credentials, or config paths. The only filesystem access is to feeds.json in the skill directory and optional user-specified save paths, which matches the documented save behavior.
✓
Persistence & Privilege
The skill is not always-on and does not request system-wide persistence. Saving to disk is explicitly gated behind user request (--save or explicit phrasing). It does not modify other skills or global agent settings in the instructions.
Assessment
This skill looks coherent for an RSS-based AI-news briefing. Before installing or enabling it: (1) review feeds.json and the listed feed URLs (some are proxied via raw.githubusercontent.com/Olshansk), because those remote files can change and will be fetched by the agent; (2) note that fetching feeds will make outbound requests to those feed hosts (server logs/IPs), which is normal for aggregators; (3) the skill only writes briefing files when you explicitly request --save — if you automate it (cron/job), double-check the save path and delivery channel configuration (e.g., Telegram chat IDs) so you don't inadvertently publish private data; (4) if you want tighter control, restrict autonomous invocation for the agent or review/approve runs before saving or announcing; and (5) if you require higher assurance, inspect the upstream GitHub repo (https://github.com/tensakulabs/ai-news-skill) and the Olshansk feed sources to confirm they meet your trust criteria.

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

ai news tldr hackernews decoder morning briefingvk972t9w8b8h9hm8rw012yhzk0s83f6bzlatestvk972t9w8b8h9hm8rw012yhzk0s83f6bz

License

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

Runtime requirements

📰 Clawdis

Comments