ai-news-radar — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ai-news-radar (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Searches and summarizes the main recent Artificial Intelligence news from curated sources.
The skill:
Invoke with:
/ai-news-radarOptionally, the user can specify the number of items:
Use these sources:
If the user specifies a quantity:
Otherwise:
Maximum:
Prioritize news items that are:
If the same news item appears in more than one source:
Classify each news item into one of these categories:
Return the list in English using the following format:
## 1. [News title](link)
**Category:** Product launch
**Main source:** Source name
**Also appeared in:** Source 2, Source 3
**Date:** MM/DD/YYYY, if available
Short paragraph explaining what happened, why it matters, and the potential impact. Do not write more than 4 lines.
---
## 2. [News title](link)
**Category:** Research
**Main source:** Source name
**Also appeared in:** —
**Date:** MM/DD/YYYY, if available
Short paragraph explaining what happened, why it matters, and the potential impact.If any feed fails:
Never interrupt the full briefing because of a partial failure.
Always respond in English. Never copy the full text of an article. Always summarize. Always include the original link. Do not invent information. Do not repeat duplicate news items. Prioritize clarity. Prioritize original sources whenever possible.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.