News Summary

This skill should be used when the user asks for news updates, daily briefings, or what's happening in the world. Fetches news from trusted international RSS feeds and can create voice summaries.

Security Scan

The skill's behavior (fetch RSS feeds and call an OpenAI TTS endpoint) matches its description, but the runtime instructions reference an API key ($OPENAI_API_KEY) that is not declared in the manifest and the skill's source/homepage is unknown — this mismatch warrants caution.

Purpose & Capability

Name/description (news summaries + optional voice) align with the runtime instructions: the SKILL.md fetches RSS feeds (BBC, Reuters, NPR, Al Jazeera), parses headlines, summarizes, and optionally calls a TTS endpoint. The listed feeds and parsing steps are coherent with the stated purpose.

Instruction Scope

Instructions are mostly scoped to fetching and summarizing RSS feeds, but they explicitly call the OpenAI TTS API using an environment variable ($OPENAI_API_KEY) that is not declared in the skill metadata. The SKILL.md also writes an output file (/tmp/news.mp3). The missing declaration of required credentials is an inconsistency that affects runtime behavior and privacy expectations.

Install Mechanism

Instruction-only skill with no install spec and no code files — low persistence and no install-time downloads. This is the lowest-risk install mechanism.

Credentials

The instructions require an OpenAI API key to generate voice summaries (Authorization: Bearer $OPENAI_API_KEY), but the manifest lists no required env vars or primary credential. Requesting or using an API key to send user content to a third-party (OpenAI) should be explicitly declared so users can make an informed choice.

Persistence & Privilege

The skill does not request always-on presence, does not install or modify other skills, and has no install hooks. Autonomous invocation (disable-model-invocation: false) is the platform default and not a special privilege here.

What to consider before installing

This skill appears to do what it says (pull RSS feeds and summarize them), but the runtime instructions call OpenAI's TTS API using $OPENAI_API_KEY while the skill metadata does not declare any required credentials. Before installing or enabling it, consider: - Do you trust this unknown skill author? There is no homepage or source listed. - If you provide an OpenAI API key, the skill will send summary text to api.openai.com; use a dedicated key with limited scope/billing controls if possible. - Ask the author to update the manifest to declare required env vars (OPENAI_API_KEY) so its permissions are transparent. - If you run it, note it will write /tmp/news.mp3; run in an environment where temporary files and network access are acceptable. - If you need extra caution, run the steps locally or in a sandbox (manually curl the feeds and generate TTS) rather than granting the skill runtime access to your credentials. If the missing OPENAI_API_KEY declaration were fixed and the author/source verified, this skill would be coherent for its purpose.

Overview

Fetch and summarize news from trusted international sources via RSS feeds.

RSS Feeds

BBC (Primary)

# World news
curl -s "https://feeds.bbci.co.uk/news/world/rss.xml"

# Top stories
curl -s "https://feeds.bbci.co.uk/news/rss.xml"

# Business
curl -s "https://feeds.bbci.co.uk/news/business/rss.xml"

# Technology
curl -s "https://feeds.bbci.co.uk/news/technology/rss.xml"

Reuters

# World news
curl -s "https://www.reutersagency.com/feed/?best-regions=world&post_type=best"

NPR (US perspective)

curl -s "https://feeds.npr.org/1001/rss.xml"

Al Jazeera (Global South perspective)

curl -s "https://www.aljazeera.com/xml/rss/all.xml"

Parse RSS

Extract titles and descriptions:

curl -s "https://feeds.bbci.co.uk/news/world/rss.xml" | \
  grep -E "<title>|<description>" | \
  sed 's/<[^>]*>//g' | \
  sed 's/^[ \t]*//' | \
  head -30

Workflow

Text summary

1. Fetch BBC world headlines
2. Optionally supplement with Reuters/NPR
3. Summarize key stories
4. Group by region or topic

Voice summary

1. Create text summary
2. Generate voice with OpenAI TTS
3. Send as audio message

curl -s https://api.openai.com/v1/audio/speech \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1-hd",
    "input": "<news summary text>",
    "voice": "onyx",
    "speed": 0.95
  }' \
  --output /tmp/news.mp3

Example Output Format

📰 News Summary [date]

🌍 WORLD
- [headline 1]
- [headline 2]

💼 BUSINESS
- [headline 1]

💻 TECH
- [headline 1]

Best Practices

• Keep summaries concise (5-8 top stories)
• Prioritize breaking news and major events
• For voice: ~2 minutes max
• Balance perspectives (Western + Global South)
• Cite source if asked