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-flowsgit 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-flows)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-saml-and-oidc-flows"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-saml-and-oidc-flows/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-flows"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-saml-and-oidc-flows.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 | $0.00111 | $0.01456 |
| Opus 5 | $0.00056 | $0.00728 |
| Sonnet 5 | $0.00022 | $0.00291 |
| Haiku 4.5 | $0.00011 | $0.00146 |
Grade A, and why
auditing-saml-and-oidc-flows 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 11d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing SAML and OIDC flows: the whole trust rests on one verification
Federated login moves the trust boundary to a signed assertion from an identity provider, and the entire security rests on the relying party verifying that assertion exactly. The classic flaws are all failures of that verification: a signature checked over the wrong element, a token accepted without a signature, an audience or redirect target not pinned, a flow with no anti-replay value. Each lets an attacker present an identity that is not theirs.
When to use
- You are reviewing a SAML or OIDC integration or an identity-provider connection.
- A login trusts an externally-issued, signed assertion or token.
- You are assessing account-linking and how an external identity maps to a local one.
Scope check
Audit login flows you own or are authorized to test, with test accounts and a test identity provider. Do not forge assertions against systems you do not control. If you can't name the authorization, stop.
The loop
-
Identify the trusted assertion and where it is verified. Find the token or assertion the relying party trusts (a signed SAML assertion, an OIDC id token) and the exact code that validates it. Everything downstream trusts whatever that check accepts, so the check is the audit target.
-
Test signature presence and coverage. Is every accepted assertion actually signed, and is the signature verified over the exact element whose contents are used? Try stripping the signature (does an unsigned assertion get accepted), and try signature wrapping (add a second, attacker-controlled assertion the app reads while the signature still validates over the original). A signature that does not cover the data the app consumes is no signature.
-
Verify audience, issuer, and expiry. Does the relying party confirm the assertion was issued for it (audience or client id), by the expected issuer, and still valid (not expired, not before)? An assertion minted for another service, or by an unexpected issuer, must be rejected. Missing audience pinning lets a token from elsewhere be replayed here.
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.
- 11d ago First seen · 126 lines · 111 tokens per session scan A 77bd228374af
auditing-saml-and-oidc-flows is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 2d ago), licensed MIT. It adds 111 tokens to every session and 1,456 once invoked, about $0.0006 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.