Cctv News Fetcher Conflict

Fetch and parse news highlights from CCTV News Broadcast (Xinwen Lianbo) for a given date.

Security Scan

The skill's code and runtime instructions match its stated purpose (fetching and parsing CCTV news); it does network fetching but requests no credentials or elevated privileges.

Purpose & Capability

Name/description (fetch CCTV Xinwen Lianbo highlights) align with included script and declared dependency (node-html-parser). The script fetches CCTV pages and extracts titles/content, which is coherent with the skill purpose.

Instruction Scope

SKILL.md tells the agent to run the bundled JS crawler with bun/node and parse its JSON output — this matches the code. Minor note: the README emphasizes bun but node should also run (depending on Node version); the skill does outbound HTTP requests to URLs discovered in the crawled pages (expected for a web crawler).

Install Mechanism

There is no install spec (instruction-only). Dependencies are standard npm packages listed in package.json/package-lock; nothing is downloaded from unexpected hosts and no archive extraction is declared.

Credentials

The skill declares no required env vars or credentials and the code does not read environment variables or sensitive config. The script does set a hard-coded Cookie and Host header for requests (likely for compatibility) but does not exfiltrate secrets.

Persistence & Privilege

always is false and the skill does not request persistent system-level settings or modify other skills. Autonomous invocation is allowed (platform default) but not combined with any broad credential access.

Assessment

This skill appears to do what it claims: it runs a bundled JS crawler that makes outbound HTTP requests to CCTV domains and returns parsed JSON. It does not ask for credentials or access local files. Before installing, consider: (1) verify the skill source/owner (there is a small ownerId mismatch in metadata), (2) run the script in a sandbox or restricted environment if you are concerned about outbound requests, and (3) ensure your runtime has a compatible Node/Bun and the node-html-parser dependency. Also note the script follows links discovered on pages, so it will fetch any URLs the site exposes — if you need stricter network controls, run it behind a proxy or limit network access.

CCTV News Fetcher

This skill allows you to fetch summary titles and content from the CCTV News Broadcast for any specific date.

Usage

You can ask the agent to:

• "Fetch CCTV news for 20250210"
• "Give me the news highlights for yesterday"

Instructions

When the user asks for news from a specific date:

1. Format the date as YYYYMMDD. If the user says "yesterday" or "today", calculate the date relative to the current local time.
2. Execute the script at {baseDir}/scripts/news_crawler.js using bun or node.
   • Command: bun {baseDir}/scripts/news_crawler.js <YYYYMMDD>
3. Parse the JSON output and summarize it for the user. Group news by "Domestic" and "International" if possible based on titles, or just list the highlights.

Configuration

The skill depends on node-html-parser. Ensure bun is installed in the environment.