monthly-update-detector — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited monthly-update-detector (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.
Validated finding (cont-19.9-M brief): monthly-updated skills outrank 90-day-stale ones in every skill marketplace tested. So the registry needs to know which skills have decayed. But auto-bumping `last_updated` to game ranking is fraud — it teaches the system to lie to itself. This skill detects, never edits.
--dry-run — count + report path, no writes--digest-only — write Sunday digest from latest 7 daily reports--threshold-days N (default 25) — staleness cutoff--out-dir <path> (default <repo>/data/curator/)STATUS=ok scanned=<n> stale=<m> threshold_days=<d> report=<path> — daily scanSTATUS=ok mode=digest week_stale=<n> message_path=<path> — Sunday digestSTATUS=ok-dryrun ...data/curator/stale-skills-<YYYY-MM-DD>.md: one line per stale skill, sorted by quality_score descending, with: name, owner_agent, days-since-update, quality_scoredata/curator/stale-digest-<YYYY-MM-DD>.md: ≤15 lines for Telegramstale-digest-*.md)data/.well-known/skills/index.json is missing, fall back to direct registry walk — never block.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.