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-device-code-and-pkce-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-device-code-and-pkce-flows)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-device-code-and-pkce-flows"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-device-code-and-pkce-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-device-code-and-pkce-flows"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-device-code-and-pkce-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 | $0.00188 | $0.02135 |
| Opus 5 | $0.00094 | $0.01068 |
| Sonnet 5 | $0.00038 | $0.00427 |
| Haiku 4.5 | $0.00019 | $0.00214 |
Grade A, and why
auditing-device-code-and-pkce-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 9d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing proof-key and device-code grants: when a code becomes a token without proof
The proof-key exchange and the device-authorization grant both exist to close one gap: a authorization code, on its own, can be intercepted, and a short user code can be guessed. Each grant adds a proof that binds the token request to the party that actually started the flow, a verifier that only the real client knows, or a device code that only the real device holds. The server side is where that proof is enforced, and where it is quietly not. When the token endpoint issues without checking the verifier, honors a downgraded challenge, or hands tokens for a device code it never bound to a client, an intercepted or guessed code becomes a live token. You find these by reading the issuance path and asking what proof it demands before it mints a token.
When to use
- The code implements or wraps a token endpoint that redeems an authorization code, or a device-authorization grant.
- A public client (one that cannot hold a secret) relies on the proof key as its protection against code interception.
- You want to know whether a captured code, a downgraded challenge, or a guessed user code yields a token.
Scope check
Exercise token and device-authorization endpoints only on systems you own or are authorized to assess, with test clients and test accounts. A confirmed issuance bypass is an authentication bypass, so treat it as account-takeover-grade and coordinate. If you can't name the authorization, stop.
The loop
- Map the issuance endpoints and whether a conformant server owns them. Find the token endpoint and, if present, the device-authorization and approval endpoints. Determine whether issuance is delegated to a conformant authorization server or handled in application code. If it proxies to a conformant server that enforces the proof, the local absence of a check is not the bug; confirm the delegation actually covers this path before reading further.
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.
- 9d ago First seen · 139 lines · 188 tokens per session scan A 9d259c45f119
auditing-device-code-and-pkce-flows is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed today), licensed MIT. It adds 188 tokens to every session and 2,135 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
protect
Add Arcjet request protection to JavaScript and TypeScript HTTP handlers. Use when protecting Next.js, Express, Fastify, SvelteKit, Remix, Astro, Nuxt, Bun, Deno, NestJS, or Node.js routes with rate limiting, bot detection, Shield, email validation, or sensitive info detection.
create-auth-skill
Scaffold and implement authentication in TypeScript/JavaScript apps using Better Auth. Detect frameworks, configure database adapters, set up route handlers, add OAuth providers, and create auth UI pages. Use when users want to add login, sign-up, or authentication to a new or existing project with Better Auth.
fhir-developer-skill
FHIR API development guide for building healthcare endpoints. Use when: (1) Creating FHIR REST endpoints (Patient, Observation, Encounter, Condition, MedicationRequest), (2) Validating FHIR resources and returning proper HTTP status codes and error responses, (3) Implementing SMART on FHIR authorization and OAuth…
api-security
Reviews REST and GraphQL APIs against the OWASP API Security Top 10:2023. Auto-invoked when reviewing OpenAPI/Swagger specs, API endpoint code, or GraphQL schemas. Covers BOLA, BFLA, authentication, rate limiting, and SSRF. Produces findings mapped to API1-API10 with remediation guidance.
create-auth-skill
Scaffold and implement authentication in TypeScript/JavaScript apps using Better Auth. Detect frameworks, configure database adapters, set up route handlers, add OAuth providers, and create auth UI pages. Use when users want to add login, sign-up, or authentication to a new or existing project with Better Auth.
api-breaker
Automated API security testing starting from domains. Discovers REST, GraphQL, and SOAP APIs, reconstructs schemas, and tests for BOLA/IDOR, BFLA, mass assignment, JWT attacks, rate limiting bypass, and business logic flaws. Use when user asks to "test API security", "break API", "find API vulnerabilities", "test…