Big AI NEWS from multiple technews sources
v1.0.0Aggregate and deduplicate AI news from multiple Chinese and English tech news sources into a single merged digest. Use when the user asks for "AI news", "AI...
⭐ 0· 33·0 current·0 all-time
byJay@goog
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (multi-source AI news aggregator) matches the instructions (fetch listed news sites, deduplicate, categorize, and produce a merged digest). The declared default sources and the workflow are appropriate for the stated purpose. One minor note: the description implies both Chinese and English sources but the default source list is primarily Chinese/Taiwanese — not a security issue but a functional limitation.
Instruction Scope
The SKILL.md only instructs web fetch/search of public news pages, extraction of title/brief/link, deduplication, categorization, and formatted output. It does not instruct reading local files, environment variables, or posting data to unexpected external endpoints. It does assume the agent platform provides 'web_fetch' and 'web_search' tools; if those tools are unavailable or require separate credentials, the skill may fail to run.
Install Mechanism
No install spec and no code files are present (instruction-only), so nothing is written to disk or installed. This is the lowest-risk install model and is proportional to the task.
Credentials
The skill requests no environment variables, credentials, or config paths. That aligns with its purpose of fetching public web content and producing a digest — no sensitive access is requested.
Persistence & Privilege
The skill is not always-enabled and does not request elevated persistence. It allows normal autonomous invocation (platform default) but does not ask to modify other skills or agent-wide settings.
Assessment
This skill appears to do what it says: fetch public news pages, deduplicate, categorize, and return a digest. Before installing, consider: (1) the skill assumes your agent has web_fetch/web_search capabilities — if your platform requires API keys for those tools, make sure those are provided by the platform and are acceptable to you; (2) the default sources are mainly Chinese/Taiwanese — if you want broader English coverage, ask for additional sources or confirm the skill will use general web_search fallback; (3) it does network fetching of external sites (public URLs) — if you have policies restricting outbound web access, note this behavior; (4) the skill requests no secrets or file access, so it does not appear to exfiltrate local data. If those points are acceptable, the skill is coherent and proportionate to its stated purpose.Like a lobster shell, security has layers — review code before you run it.
latestvk977gky08191cy04m9dy3rxsv5842xrk
License
MIT-0
Free to use, modify, and redistribute. No attribution required.