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-saml-and-oidc-federation-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-saml-and-oidc-federation-trust)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-saml-and-oidc-federation-trust"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-saml-and-oidc-federation-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-saml-and-oidc-federation-trust"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-saml-and-oidc-federation-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 | $0.00183 | $0.02127 |
| Opus 5 | $0.00092 | $0.01064 |
| Sonnet 5 | $0.00037 | $0.00425 |
| Haiku 4.5 | $0.00018 | $0.00213 |
Grade A, and why
auditing-saml-and-oidc-federation-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 12d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing SAML and OIDC federation trust: the assertion is only as good as its verification
Federated login moves the authentication decision to an identity provider and hands the relying party a signed assertion, a SAML response or an OIDC ID token, that says who the user is. The relying party's entire security then rests on verifying that assertion correctly, and the ways to verify it incorrectly are well worn. SAML signature wrapping slips an unsigned, attacker-authored assertion alongside a signed one so the application reads the wrong element; a signature checked over the wrong scope, or not at all, accepts a tampered response. An OIDC ID token whose issuer, audience, or nonce goes unchecked can come from the wrong provider, be minted for a different application, or be replayed. And a relying party that trusts a subject or email in the assertion without binding it to the verified issuer will authenticate any user an attacker names. The audit is not whether federation is configured but whether a forged or misbound assertion is refused. You audit this by testing each validation the relying party must perform on the assertion.
When to use
- A relying party consumes SAML assertions or OIDC ID tokens from an identity provider to authenticate users.
- Signature, issuer, audience, or nonce validation on the assertion may be missing or scoped wrong.
- The relying party may trust a subject, email, or attribute without binding it to the verified issuer.
Scope check
Test federation trust only against relying parties and identity providers you own or are authorized to assess, on non-production accounts. Forging or replaying assertions attempts real authentication, so use non-production identities and never authenticate as a real user. If you can't name the authorization, stop.
The loop
- Establish the intended trust first. Name which identity provider and signing key the relying party should trust, the expected issuer and audience, and how the assertion's subject maps to a local user. This is the false-positive killer: a relying party that verifies the signature over the correct element against the expected key, checks issuer, audience, and nonce, and binds the subject to the verified issuer is correct. Name the intended trust, then test each check.
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.
- 12d ago First seen · 140 lines · 183 tokens per session scan A 83ed94736b6e
auditing-saml-and-oidc-federation-trust is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 4d ago), licensed MIT. It adds 183 tokens to every session and 2,127 once invoked, about $0.0009 per session on Opus 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 2026-08-31.
Other skills, from other repositories
prodcheck-review
Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations and post-launch readiness. 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 citations…
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-langgraph
Integrate Arcjet security into a LangGraph Graph API agent using @arcjet/guard — wrap tool() / StructuredTool, wrap ToolNode for unwrapped MCP tools, and read threadid for correlation. Use when asked to add Arcjet to a LangGraph StateGraph / ToolNode agent, rate limit its tools, screen inbound messages, or block…
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.