capture-link — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited capture-link (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Given a URL and optional notes, assess whether the link is worth acting on and produce an org-mode capture snippet.
URL: the link to evaluateNOTES (optional): why the user flagged it, context, rough idea of what they want to do with itweb_fetch. Cap at one page — do not follow links or read referenced docs. If the fetch fails or returns nothing useful, say so in the verdict and still produce the snippet with what you know.VERDICT: [KEEP|DROP] — <one sentence reason>Then the org snippet:
* TODO [[<url>][<page title from fetched content>]] :bookmark:idea:
[<today's date as YYYY-MM-DD Day>]
- what it is: <one sentence, factual, from the page>
- why i flagged it: <from NOTES if provided, otherwise infer from page content>
- effort: <your best guess, plain english, e.g. "~1h to try the basics", "likely a half-day integration">
- action: <single concrete first step, imperative, specific — not "look into it">org, no ``, nothing). Raw text only.[2026-02-23 Mon] — match org inactive timestamp style.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.