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-mfa-enrollment-and-reset-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/auditing-mfa-enrollment-and-reset-abuse)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-mfa-enrollment-and-reset-abuse"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-mfa-enrollment-and-reset-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/auditing-mfa-enrollment-and-reset-abuse"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-mfa-enrollment-and-reset-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 | $0.00205 | $0.02383 |
| Opus 5.5 | $0.00082 | $0.00953 |
| Sonnet 5.5 | $0.00041 | $0.00477 |
| Haiku 4.5 | $0.00020 | $0.00238 |
Grade A, and why
auditing-mfa-enrollment-and-reset-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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing MFA enrollment and reset abuse: the second factor is only as strong as how you enroll and reset it
Multi-factor authentication assumes the attacker who has the password still cannot pass the second factor, and that assumption lives or dies in three places most audits skip: how a factor is enrolled, how it is reset or recovered, and how a step-up is enforced. If an account with only the first factor satisfied can enroll a new authenticator without re-proving identity, an attacker with a stolen password simply adds their own second factor and now passes MFA legitimately. If the reset or recovery flow is guarded only by a weak signal, an email link to an inbox the attacker controls, a knowledge question, a support request that does not verify hard, then MFA resets back to attacker control and the second factor is decorative. If a step-up prompt on a sensitive action can be skipped, or backup codes are weak, reusable, or handed out without authentication, or a push approval lands on a single tap so fatigue or bombing gets an accidental yes, the factor is bypassed rather than broken. The audit treats enrollment and reset as privileged actions that must re-prove identity, and checks that every step-up is actually enforced. You audit this by holding only the first factor and trying to add, reset, or skip the second.
When to use
- An authentication system lets users enroll a second factor, reset or recover it, use backup codes, or satisfy a step-up prompt.
- Enrollment or reset may not re-prove identity, or recovery may be guarded only by a weak signal (email link, knowledge question, support request).
- Step-up may be skippable, backup codes may be weak or unauthenticated, or push approval may succeed on a single tap (MFA fatigue).
Scope check
Test MFA enrollment and reset only against accounts and systems you own or are authorized to assess, with test accounts. Enrolling, resetting, and bypassing factors changes real authentication state, so use test identities and never add a factor to, reset, or take over an account 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 · 149 lines · 205 tokens per session scan A 4508478e54c6
auditing-mfa-enrollment-and-reset-abuse is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 205 tokens to every session and 2,383 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.