bootstrap — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited bootstrap (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.
Connect the right OrbiAds tenant to the right Google Ad Manager account, verify credentials, and return a confirmed session packet.
tenantId or networkCode in the current session.Do not use if tenantId and networkCode are already confirmed — reuse the session packet instead.
get_my_tenant_id — mandatory first call. [free]check_credentials + get_network_info in parallel if no trusted session packet. [free]initiate_gam_auth, open browser URL, poll with poll_auth_status. [free]list_accessible_networks, ask user to choose, then select_gam_network. [free]switch_network. [free]get_credit_balance before billed downstream work. [free]Wrap the result in <handoff> tags:
<handoff>
tenantId: ...
networkCode: ...
authStatus: completed | pending | select_network | expired
networkInitialized: true | false
nextRecommendedSkill: inventory-ad-units
</handoff>Use an artifact table when list_accessible_networks returns more than one result. Apply extended thinking before deciding between full bootstrap and switch_network only.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.