AI news hub, powerful
v1.1.3Aggregate and rank AI and tech news from multiple user-defined sources in source.md, filtering to the latest 24-hour articles with summaries and source links.
⭐ 0· 107·0 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
medium confidencePurpose & Capability
The skill's name and description align with the instructions: it reads a user-provided list of news sites and aggregates recent articles. It does not request unrelated credentials or installs. Minor mismatch: the top-level description refers to 'workspace/source.md' while the Workflow step refers to 'workspace/skills/more-news/source.md' — that ambiguity could cause the agent to look in different locations.
Instruction Scope
Runtime instructions are narrowly focused on fetching articles from the listed URLs, filtering to the last 24 hours, summarizing, ranking, and reporting skipped sources. Two scope issues to watch: (1) the path inconsistency (which file to read) could cause the agent to search other workspace locations; (2) the explicit fallback to 'web_search' if all sources are blocked broadens the sources the agent will query beyond the provided list. Neither is clearly malicious, but both expand what the agent will read/fetch.
Install Mechanism
Instruction-only skill with no install spec and no code files — nothing is written to disk and no external packages are pulled in.
Credentials
The skill requests no environment variables, secrets, or config paths. All required inputs are the workspace source file and public web URLs in that file, which is proportionate to the stated purpose.
Persistence & Privilege
always is false, the skill does not request persistent privileges or modify other skills' configuration; autonomous invocation is allowed by platform default and is not, by itself, a concern here.
Assessment
This skill appears coherent for aggregating news, but before installing: (1) confirm which path the skill will read (workspace/source.md vs workspace/skills/more-news/source.md) so it does not accidentally read unintended files; (2) inspect source.md and remove any private or sensitive URLs you don't want the agent to fetch; (3) consider disabling or limiting the 'fallback to web_search' behavior if you want results strictly from the listed sources; and (4) if you have concerns about the agent fetching paywalled or geo-restricted sites, test behavior with a small set of benign sources first.Like a lobster shell, security has layers — review code before you run it.
latestvk976thnah4sh568zhwzzwgd6ds84d0mt
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
