Ai News Collector
PassAudited by ClawScan on May 11, 2026.
Overview
This instruction-only skill coherently tells the agent to collect AI news from public web sources, with only minor browsing and provenance notes to be aware of.
This skill is reasonable to install if you want Chinese AI-news summaries. Expect it to perform multiple public web searches and fetch webpages; verify important news items from the cited links, and note the minor registry/package metadata mismatch.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The agent may visit many public websites and summarize untrusted external content while answering AI-news questions.
The skill explicitly directs the agent to use web search and web_fetch repeatedly. This is expected for a news aggregation skill, but it means the agent will browse and process third-party web content.
多维度分层搜索（最少 8 次，建议 10-12 次） ... 发现周报后，用 web_fetch 获取全文
Use it for public-news queries, and treat fetched webpages as sources to summarize rather than instructions for the agent to follow.
The skill behavior appears benign, but the metadata inconsistency may make provenance or package identity slightly less clear.
The packaged metadata differs from the registry metadata shown for this evaluation, which lists a different owner ID and the slug "ai-news-collector". Because there is no code or install step, this is a provenance note rather than evidence of unsafe behavior.
"ownerId": "kn7fr165ff9vkkwsqyqrq2nwas80t4ev", "slug": "ai-news-collectors"
Verify that the registry listing and packaged metadata are from the intended publisher before relying on the skill.