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 auditing-scim-provisioning-trustgit 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/auditing-scim-provisioning-trust)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-scim-provisioning-trust"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-scim-provisioning-trust/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/auditing-scim-provisioning-trust"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-scim-provisioning-trust.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 | $0.00204 | $0.02388 |
| Opus 5.5 | $0.00082 | $0.00955 |
| Sonnet 5.5 | $0.00041 | $0.00478 |
| Haiku 4.5 | $0.00020 | $0.00239 |
Grade A, and why
auditing-scim-provisioning-trust 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing SCIM provisioning trust: the provisioning token creates admins, so guard it like one
SCIM lets an identity provider create, update, and delete accounts in a service provider automatically, and that means the SCIM endpoint is an account-and-group factory reachable over the network. Whoever can call it with a valid credential can mint users, add them to privileged groups, and change who an existing account belongs to, so the provisioning credential is effectively an admin credential and the trust in the calling identity provider is the whole boundary. The failures follow. A provisioning endpoint authenticated by a weak, shared, or never-expiring bearer token hands account creation to anyone who obtains it. A handler that does not scope requests to the calling tenant lets one customer's provisioning client touch another customer's users. A group or role pushed over SCIM that maps to more privilege than the source attribute warrants is a quiet escalation. A deprovisioning event that does not actually disable the account leaves a departed user with standing access. And attribute updates, email, external id, an admin flag, trusted without validation let an attacker reassign or elevate an account. The audit treats the SCIM endpoint as privileged, checks its authentication and tenant scoping, and follows each lifecycle event to what it actually grants or revokes. You audit this by calling the SCIM API as the identity provider would and as an attacker who stole its token would.
When to use
- An identity provider provisions accounts and groups into a service provider over SCIM 2.0 (create, update, deactivate, delete).
- The SCIM endpoint may be authenticated by a shared, weak, or long-lived bearer token.
- Provisioning may not be scoped per tenant, deprovisioning may not revoke access, or attribute mappings may over-grant.
Scope check
Test SCIM provisioning only against services and directories you own or are authorized to assess, on non-production tenants. Creating, modifying, and deleting accounts over SCIM changes real identity state, so use test tenants and never provision, elevate, or delete accounts that are 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 · 152 lines · 204 tokens per session scan A 0a13a85bc4cb
auditing-scim-provisioning-trust is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 204 tokens to every session and 2,388 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.