personalized-news-collector

Get current news which matches user's recent interests. It can be triggered when user ask about current news or the events happening around without selecting...

Security Scan

The skill's requirements and instructions are consistent with a personalized news-collector: it reads conversation history to infer interests and fetches public news feeds, with no hidden installs or requested credentials — but its runtime instructions are vague about data handling and network scope, so review privacy/usage expectations before enabling.

Purpose & Capability

Name and description match the instructions: the skill summarizes user interests from recent conversation history and fetches news matching those interests. It does not request unrelated credentials, binaries, or system paths.

Instruction Scope

SKILL.md tells the agent to infer interests from recent memory/conversation history and to fetch many external RSS/JSON endpoints (examples provided in sources.md). This is expected for a personalized news aggregator, but the instructions are broad ("collect as much information"), give the agent wide discretion about which external URLs to query, and do not specify limits on how conversation memory is used or retained — raising privacy and data‑exfiltration considerations.

Install Mechanism

There is no install specification and no code files — the skill is instruction-only, so nothing will be written to disk or installed at install time.

Credentials

The skill requests no environment variables, credentials, or config paths. Its need to access conversation history is proportional to personalization and is declared in the instructions.

Persistence & Privilege

The skill is not marked always:true and does not request persistent privileges or modifications to other skills or system settings. It is user-invocable and may be called autonomously (platform default).

Assessment

This skill appears to do what it says: infer your interests from recent conversation and fetch news from public RSS/JSON feeds. Before installing, consider: (1) privacy — the skill explicitly reads recent memory/conversation history to summarize interests, so confirm you are comfortable with that access; (2) network use — it will make outbound requests to many external URLs (the provided sources.md lists reputable feeds, but the instructions allow querying other sites), so ensure your environment's network policy and rate limits are acceptable; (3) content handling — the skill does not specify retention, filtering, or sanitization rules for fetched content, so be cautious about forwarding or storing fetched items containing private data or HTML/JS; (4) supply and trust of sources — review sources.md and remove any feeds you don't trust. If you want tighter control, ask for the skill to be modified to (a) limit sources to an allowlist, (b) require explicit user consent to read conversation memory, and (c) enforce a maximum number of requests and explicit data retention rules.

Analyze user's current interests and collect current news concerning these interests. Finally deliver a report which has categorized the collected news and sort it by popularity.

Working Process

1. Analyze Interests

All the news conllected news should match user's interests. User's interests can be summarized from recent memory and conversation history. At least three main interests should be offered.

2. Collect News

Get news concerning user's interests. You should collect as much as Information from different sources. You can use the command like:

curl -sL `the url of informtion source`

You can use the URLs offered at sources.md as your news sources, but some of them may not be available and they should not be your only choices. You are supported to collect Information from more sources, especially when user's interests are not included in sources.md.

3.Summary News

After collecting news whose topic matches user's interests, some news may appear in different sources at the same time. Judge the importance of the news based on its frequency of appearance in different sources(if two news items' frequency is the same, judge the importance according to your own opinion), and rank the news in descending order of importance.

4.Output

There should be at least three news items for one interest. Your output should follow the format below:

1. "user's first interest" "The news with the highest importance under this interest." "The news with the second highest importance under this interest." "The news with the third highest importance under this interest."
2. "user's second interest" "The news with the highest importance under this interest." "The news with the second highest importance under this interest." "The news with the third highest importance under this interest." ...........