ClawHub

Nature and science AI news

v1.9.0

Fetch and summarize the latest AI-related articles from Nature's RSS feed and the top 7 AI news from New Scientist Technology. Use when the user asks for Nat...

⭐ 0· 40·0 current·0 all-time
byJay@goog
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description match the instructions: the SKILL.md explicitly fetches Nature's RSS and New Scientist Technology pages and summarizes AI-related items. No unrelated credentials, binaries, or config paths are requested.
ℹ
Instruction Scope
Instructions stay within the stated scope (only web_fetch calls to two known sources, parsing and filtering). Minor implementation assumptions: it expects Nature items to include <dc:date> in YYYY-MM-DD and uses a 3-day window for Nature; the keyword list is broad (includes terms like 'quantum computing', 'encryption', 'chip', 'data centre') which may return non-AI items depending on how strictly 'AI-related' is interpreted. Also, New Scientist content or articles may be behind paywalls or structured differently, which could affect extraction—these are operational notes, not security issues.
✓
Install Mechanism
No install spec and no code files are present (instruction-only). This is the lowest-risk install pattern; nothing is downloaded or written to disk by the skill itself.
✓
Credentials
The skill requires no environment variables, credentials, or config paths. The declared inputs align with the task (public web fetches) and there is no disproportionate access requested.
✓
Persistence & Privilege
always is false and the skill does not request elevated or persistent privileges or modify other skills. Autonomous invocation is allowed by default but not excessive in this skill's context.
Assessment
This skill appears coherent and low-risk: it only fetches public webpages and parses them, and it asks for no secrets or installs. Before enabling, consider: (1) the keyword list is broad and may surface items that are not strictly AI-related — you may want to refine it; (2) Nature and New Scientist pages sometimes use different date tags or paywalls, so results could be incomplete; (3) verify that your agent's web_fetch respects robots.txt and site terms to avoid scraping policy issues. If you need guaranteed coverage or paid-article access, the skill will need additional credentials or API access, which it currently does not request.

Like a lobster shell, security has layers — review code before you run it.

latestvk977vt4c569nd09tknxxd7wyfs847rga

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments