Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add UnboundCompute/security-agent-skills --skill hunting-tenant-onboarding-and-discovery-abusegit clone --depth 1 https://github.com/UnboundCompute/security-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-tenant-onboarding-and-discovery-abuse)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-tenant-onboarding-and-discovery-abuse"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-tenant-onboarding-and-discovery-abuse/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-tenant-onboarding-and-discovery-abuse"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-tenant-onboarding-and-discovery-abuse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00203 | $0.02437 |
| Opus 5.5 | $0.00081 | $0.00975 |
| Sonnet 5.5 | $0.00041 | $0.00487 |
| Haiku 4.5 | $0.00020 | $0.00244 |
Grade A, and why
hunting-tenant-onboarding-and-discovery-abuse scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunting tenant onboarding and discovery abuse: how you get into an organization decides who is inside it
In multi-tenant SaaS the organization is the trust boundary, and onboarding is how someone gets put inside it, so the onboarding flow decides membership as surely as any access-control check. The trouble is that onboarding is built for growth, self-service signup, easy domain-based joining, frictionless invitations, and growth-shaped defaults are exactly where an attacker walks in. A signup that auto-joins a new user to an existing organization because their email domain matches lets anyone who can get an address at that domain, or spoof one, land inside the tenant with whatever a member sees. A domain-claim step that can be satisfied without truly proving ownership lets an attacker claim a domain and, with it, the users under it. An invitation whose token is guessable, reusable, or not bound to the address it was sent to lets an attacker redeem someone else's invite. A tenant-discovery endpoint that answers which organizations exist or which domains are registered hands an attacker the map. And a first-admin or org-creation race, where claiming an as-yet-unclaimed organization makes you its admin, grants authority over everyone who later joins. The hunt walks every way in, and every way to learn a tenant exists, and checks that each proves what it claims. You hunt this by trying to join, claim, or enumerate a tenant you have no right to.
When to use
- A multi-tenant application lets users sign up, create or claim organizations, verify domains, or accept invitations to join a tenant.
- Signup may auto-join by email domain, domain verification may not prove ownership, or invitations may be guessable, reusable, or unbound to the invited address.
- A tenant-discovery endpoint may reveal which organizations or domains exist, or claiming an unclaimed org may grant admin.
Scope check
Test tenant onboarding and discovery only against applications and organizations you own or are authorized to assess, on test tenants. Joining, claiming, and enumerating tenants touches real organization membership and data, so use test organizations and never join, claim, or enumerate a tenant that is not yours. If you can't name the authorization, stop.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 156 lines · 203 tokens per session scan A 2ed47fcd4945
hunting-tenant-onboarding-and-discovery-abuse is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 203 tokens to every session and 2,437 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
prodcheck-review
Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations, post-launch readiness and people. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line…
integrate-arcjet-guard-genkit
Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…
integrate-arcjet-guard-tanstack-ai
Integrate Arcjet security into a TanStack AI chat() app using @arcjet/guard — put guardMiddleware first on chat({ middleware }) so onBeforeToolCall gates tools, and read a caller-owned id from chat({ context }). Use when asked to add Arcjet to TanStack AI, rate limit its tools, screen inbound messages, or block prompt…
integrate-arcjet-guard-claude-managed-agents
Integrate Arcjet security into Claude Managed Agents (hosted REST+SSE, beta managed-agents-2026-04-01) using @arcjet/guard — screen user.message / initialevents before sessions.events.send, and gate custom tools on agent.customtooluse. Use when asked to add Arcjet to Claude Managed Agents, rate limit custom tools, or…
linear-claude-skill
Manage Linear issues, projects, and teams.
varlock-claude-skill
Secure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits.