inventory-ad-units — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited inventory-ad-units (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.
Explore the existing GAM inventory, qualify the ad units needed for a workflow, and create or push new ad units in a controlled way.
adUnitIds before placements, targeting, or forecasting.Do not use if adUnitIds are already confirmed — pass them directly to the next skill.
list_ad_units + search_ad_units + get_ad_unit_tree + audit_inventory — read first. [free]get_ad_units_by_ids. [free]dry_run=True first for any write batch.adUnitIds and residual risks.list_ad_units, search_ad_units, get_ad_unit_tree, audit_inventory, find_inactive_ad_units — [free]generate_inventory_blueprint — preview without write [free]create_ad_units_batch — write, requires dry_run=True then confirmation tokenpush_inventory_blueprint — write after human validationarchive_inactive_ad_units — destructive, human review requireddry_run preview has not been shown and approved.Render the ad-unit tree as a collapsible artifact when hierarchy > 10 nodes. Show the dry_run preview as an artifact before asking for confirmation.
<handoff>
selectedAdUnitIds: [...]
auditFindings: [...]
confirmationNeeded: true | false
nextRecommendedSkill: placements-targeting | availability-forecast
</handoff>~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.